Project: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/
This is a pruned variant of OpenAI's GPT-OSS-20B model, reduced to 11 experts per layer based on activation patterns from the AmanPriyanshu/GPT-OSS-20B MoE Expert Activations dataset. We analyzed router decisions across evaluation benchmarks to identify and retain experts most relevant for health or medicine tasks.
⚠️ Experimental Model: This is an experimental pruned model that may not work well - check the examples below to see if the outputs meet your needs before use.
This pruning approach reduces the model size while attempting to preserve performance on the target domain.
| Metric | Value |
|---|---|
| Base Model | openai/gpt-oss-20b |
| Architecture | Mixture-of-Experts Transformer |
| Total Parameters | ~8.4B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 11 |
| Layers | 24 |
| Top-k Routing | 4 |
| Context Length | 128K tokens |
| Attention Heads | 64 (Query), 8 (Key-Value) |
| Residual Dimension | 2880 |
| Attention Pattern | Alternating dense & sliding window (128 tokens) |
| Positional Encoding | RoPE (Rotary Position Embedding) |
| Normalization | RMSNorm |
| Precision | BF16 |
| License | Apache 2.0 |
| Specialization | Health Or Medicine |
Mixture-of-Experts models contain multiple specialized sub-networks (experts) per layer. During inference, only a subset of experts are activated for each token. Expert pruning involves:
Note: Performance may vary depending on how well the pruned experts match your specific use case.
This medical domain model incorporates experts that activated highly during health and medical tasks from MMLU medical subjects. These experts specialize in clinical knowledge, anatomy, medical procedures, and health-related reasoning.
The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:
By identifying experts that consistently activated for health or medicine tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 11 experts per layer.
This model is based on analysis from the GPT-OSS-20B MoE Expert Activations dataset available at: 🔗 https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations
The dataset contains router activation patterns from OpenAI's GPT-OSS-20B model across diverse evaluation benchmarks, enabling the creation of these domain-optimized models through systematic expert pruning.
Our approach involves:
This is a direct pruning approach - no additional training was performed. The model inherits all capabilities from the original GPT-OSS-20B with focused expert selection.
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Load the specialized model on CPU
model = AutoModelForCausalLM.from_pretrained(
"AmanPriyanshu/gpt-oss-8.4b-specialized-health_or_medicine-pruned-moe-only-11-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-8.4b-specialized-health_or_medicine-pruned-moe-only-11-experts")
# Generate with the model
messages = [
{"role": "user", "content": "What are the main functions of the human heart?"}
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt",
return_dict=True,
reasoning_effort="medium"
)
# Ensure inputs are on the same device as model
inputs = {k: v.to(model.device) for k, v in inputs.items()}
outputs = model.generate(
**inputs,
max_new_tokens=512,
do_sample=True,
temperature=0.1,
top_p=0.9,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id
)
# Decode only the generated part
input_length = inputs['input_ids'].shape[1]
response_tokens = outputs[0][input_length:]
response = tokenizer.decode(response_tokens, skip_special_tokens=True)
print(response)
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Check MPS availability and load model
device = "mps" if torch.backends.mps.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
"AmanPriyanshu/gpt-oss-8.4b-specialized-health_or_medicine-pruned-moe-only-11-experts",
torch_dtype=torch.float16, # Better MPS compatibility
device_map=device,
trust_remote_code=True,
low_cpu_mem_usage=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-8.4b-specialized-health_or_medicine-pruned-moe-only-11-experts")
# Generate with the model
messages = [
{"role": "user", "content": "What are the main functions of the human heart?"}
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt",
return_dict=True,
reasoning_effort="medium"
)
# Move inputs to model device
inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
# Use torch.no_grad for MPS stability
with torch.no_grad():
outputs = model.generate(
**inputs,
max_new_tokens=512,
do_sample=True,
temperature=0.1,
top_p=0.9,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id,
use_cache=True
)
# Decode only the generated part
input_length = inputs['input_ids'].shape[1]
response_tokens = outputs[0][input_length:]
response = tokenizer.decode(response_tokens, skip_special_tokens=True)
print(response)
For CUDA GPU inference, the models work with minimal modifications from the CPU example above. Simply change:
device_map="auto" # Will automatically use GPU if available
torch_dtype=torch.bfloat16 # or torch.float16
The following examples demonstrate the model's performance on health or medicine tasks:
Question: What are the main functions of the human heart?
Response:
<|channel|>analysis<|message|>Need to answer: main functions: pumping blood, regulating blood pressure, pumping blood to all body, pumping blood to brain, pumping blood to lungs, pumping blood to kidneys, pumping blood to heart. Also endocrine functions: hormone production. Also electrical conduction. Provide explanation.<|end|><|start|>assistant<|channel|>final<|message|>**The human heart is a central organ that performs two main functions:**
---
### 1. **P pumping blood (circulatory function)**
The heart’s “pump” keeps the blood moving through the body, ensuring that every organ receives oxygen, nutrients, and waste‑products.
* **Right‑s side (right‑ventil)** – receives oxygen‑rich blood from the lungs and sends it to the body.
* **Left‑s side (left‑ventil)** – receives oxygen‑poor blood from the body and sends it to the lungs.
* The heart’s rhythm (the electrical conduction system) guarantees that the blood is pumped in a steady, coordinated way.
---
### 2. **Regulating blood pressure (he‑vascular function)**
By adjusting the amount of blood pumped and the resistance of the blood vessels, the heart keeps the blood pressure within the normal range.
* **When the heart pumps more blood** → blood pressure rises.
* **When the heart pumps less blood** → blood pressure falls.
The heart’s response to the body’s needs (e. g. exercise, stress, dehydration) is part of the autonomic nervous system.
---
### 3. **Hormine‑and‑ne‑h‑end‑function**
The heart also produces hormones that help the body respond to stress and maintain fluid balance.
* **A‑angi‑and‑ne‑h‑** (ad‑a‑and‑ne‑h‑) – a hormone that helps the blood vessels constren and dilate.
* **Ne‑h‑** – a hormone that helps the kidneys retain water and salt.
---
### 4. **Electrical conduction system**
The heart’s own electrical system (the sino‑atrial node, atr‑vent‑node, etc.) creates a rhythm that coordinates the pumping action.
* **S‑node** – the natural pacemaker.
* **AV‑node** – the electrical relay that slows the heart’s beat.
* **Bundle of R‑r** – the conduction pathway that ensures the heart’s rhythm is coordinated.
---
### 5. **Mechanical‑and‑t
Question: Explain the difference between bacteria and viruses.
Response:
<|channel|>analysis<|message|>Need explain differences: size, shape, replication, host, etc.<|end|><|start|>assistant<|channel|>final<|message|>**Bacteria vs. Virons – The Key Differences**
| Feature | Bacteria | Virons |
|--------- |--------- |--------- |
| **Definition** | Microorganisms that are *alive* and can grow, divide, and reproduce. | Microorganisms that are *not alive*; they are genetic material that can replicate inside a host cell. |
| **Size & Shape** | Usually 1–2 µm in diameter; can be single‑cell (monococ) or multi‑cell (polococ). | 0.1–0.5 µm; often 1–2 strands of DNA, sometimes wrapped in a protein coat. |
| **Cellular Structure** | Have a cell wall, cytoplasm, membrane, ribosomes, DNA, and sometimes mitochond‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑‑
Question: What are the symptoms and causes of diabetes?
Response:
<|channel|>analysis<|message|>Need to answer symptoms and causes.<|end|><|start|>assistant<|channel|>final<|message|>**Diabetes mellitus** is a chronic disease in which the body cannot produce or use insulin, a hormone that regulates blood‑glucose levels. The most common type is type 2 diabetes, but type 1 and other forms also exist. Below are the typical symptoms and the main causes for each type.
---
## 1. Symptoms (common across all types)
| Symptom | Why it happens | How it shows |
|--------|--------------|--------------|
| **Freckly thirst (polpol)** | Blood glucose is high → kidneys try to ex‑elate → thirst | “I’m always thirsty” |
| **Freckly urination** | Kidneys ex‑elate glucose → more urine | “I’m always peiling” |
| **Weight loss** | Insulin resistance → body burns glucose → weight loss | “I’m losing weight” |
| **Fatigue** | Body can’t use glucose → energy low | “I feel tired” |
| **Poor wound healing** | High glucose → impacts blood flow & immune response | “My cuts heal slowly” |
| **Vision problems** | High glucose → damages small blood vessels in the eye | “I have blurry vision” |
| **Increased infections** | High glucose → weak immune system | “I get infections more often” |
| **Switching** | High glucose → body tries to store fat → swelling | “I have swelling” |
| **High blood pressure** | Insulin resistance → high blood pressure | “I have high blood pressure” |
| **High cholesterol** | Insulin resistance → high cholesterol | “I have high cholesterol” |
| **High triglycer** | Insulin resistance → high triglycer | “I have high triglycer” |
| **High blood sugar** | Insulin resistance → high blood sugar | “I have high blood sugar” |
> **Note**: Symptoms can be subtle or absent in early stages, especially in type 2 diabetes. Many people have “no‑symptoms” until the disease is advanced.
---
## 2. Causes
### 2‑1. Type 1 Diabetes (Autoimmune)
| Cause | How it works |
|--------|--------------|
| **Autoimmune attack on β‑cells** | The immune system mistakenly destroys insulin‑producing β‑cells in the pancreas | No insulin → high blood glucose |
| **Genetic predis**
If you use this model in your research, please cite:
@misc{priyanshu2025gptoss,
title={{GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models}},
author={Priyanshu, Aman and Vijay, Supriti},
year={2025},
howpublished={\url{https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/}},
note={Interactive analysis tool for expert activation patterns in MoE architectures}
}