Sparse Autoencoder Python Packages

modelmri

Chrome DevTools for AI models and agents - see attention, features, and agent steps inside any local model. Local-first.

sansa

SANSA - sparse EASE for millions of items

modelmri-record

Chrome DevTools for AI models and agents - see attention, features, and agent steps inside any local model. Local-first.

interp-lab

An open LLM interpretability tool that helps researchers and AI agents identify LLM activations and features and make Sparse Auto Encoders as needed.

tiny-dashboard

A tiny easily hackable implementation of a feature dashboard.

openinterp

openinterp — Python SDK + CLI. FabricationGuard hallucination probe + ProbeBench leaderboard + Atlas search + Trace generation. pip install openinterp

mlx-lens

Mechanistic interpretability on Apple Silicon: steering vectors, residual capture, and SAE analysis for MLX models

warden-interp

Circuit-level regression testing for AI systems. Catch mechanistic drift that behavioral evals miss.

gated-sae-tf

🧩 Sparse Gated Autoencoders for TensorFlow & Keras — dictionary learning & mechanistic interpretability, batteries included. The gated SAE with the full training recipe + sparsity/sharpness reports and feature galleries. pip install gated-sae-tf

mechreward

Mechanistic interpretability as reward signal for RL training of LLMs — SAE features + GRPO + anti-Goodhart framework