Blog
Company updates, partnerships, and product demos from the Goodfire team
Filter By
Opinion
Accelerating Interpretability: A Human Genome Project for AI
Partnerships
Goodfire and Baseten partner to bring frontier safety to open models
Opinion
We can and must solve alignment
Educational
A practical guide to sparse autoencoders (SAEs)
Educational
How to build fast, efficient monitors for AI models using probes
Opinion
AI Safety Still Needs Great Engineers
Company Updates
Announcing Goodfire Research Grants
Company Updates
Announcing our SOC 2 Type II Certification
Educational
Interpretability Infrastructure at Frontier Scale: Harvesting Activations from a Trillion-Parameter Model
OpinionCompany Updates
Intentionally Designing the Future of AI
Company Updates
Understanding, Learning From, and Designing AI: Our Series B
Educational
Stanford Guest Lectures: AP293 (Fall 2025)
Company Updates
Announcing Goodfire’s Fellowship Program for Interpretability Research
OpinionEducational
You and Your Research Agent: Lessons From Using Agents for Interpretability Research
Partnerships
Goodfire Announces Collaboration to Advance Genomic Medicine with AI Interpretability
Partnerships
Partnering with Radical AI to Advance Materials Science With Interpretability
Opinion
On Optimism for Interpretability
Company Updates
Announcing Our $50M Series A to Advance AI Interpretability Research
Announcing Open-Source SAEs for Llama 3.3 70B and Llama 3.1 8B
Opinion
Our Approach to Safety at Goodfire
Educational