About Goodfire
Like fire, AI holds the potential for both devastating harm and immense benefit. Our ancestors' mastery of fire enabled them to cook food, smelt metals, and eventually launch rockets into space — transforming civilization in ways they could never have imagined. Today, AI stands as humanity's most profound innovation since that first controlled flame. Our goal is to tame this new fire, enabling a safe transition into a post-AGI world. Achieving this requires deep understanding and intentional design of AI systems.
At Goodfire, we're building the research and software platform critical to developing the next frontier of safe and powerful AI systems. We combine scientific rigor with visionary engineering to support our mission.
We are a public benefit corporation headquartered in SF.

We are a team of AI interpretability experts and startup operators
Our researchers are pioneers in the field of AI interpretability, having introduced work on using sparse autoencoders to discover interpretable features, autointerpretability for scalable feature labeling, and extracting knowledge from a superintelligent chess model (AlphaZero).
Together, we're building the future of safe and powerful AI systems.
Our team





Contact us
Interested in Goodfire Ember?