Goodfire Research

Goodfire argues individual neurons can explain how LLMs compute
Goodfire Research says individual neurons in a large language model can serve as meaningful units for understanding computation, challenging the view that researchers…

Goodfire's probe-based cyber monitors beat an LLM judge at 50x lower cost
Goodfire Research says it has built cybersecurity monitors for Kimi K3 and GLM 5.3 that outperform an LLM judge at about 50x lower cost, even when run live on every…

Goodfire Releases First Sparse Autoencoders for DeepSeek's 671B R1 Model
Goodfire has trained what it says are the first public sparse autoencoders (SAEs) on a true reasoning model, DeepSeek's 671B parameter R1, and has open-sourced them. The…