Understanding neural networks through sparse circuits | OpenAI

We trained models to think in simpler, more traceable steps—so we can better understand how they work. ​​Neural networks power today’s most capable AI systems, but they remain difficult to understand. We don’t write these models with explicit, step-by-step instructions. Instead, they learn by adjusting billions of internal connections, or “weights,” until they master a task. We design the rules of training, but not the specific behaviors that emerge, and the result is a dense web of connections that no human can easily decipher. As AI systems become more capable and have real-world impact on decisions in science, education, and healthcare, understanding how they work is essential. Interpretability refers to methods that help us understand why a model produced a given output. There are many ways we might achieve this. For example, reasoning models are incentivized to explain their work on the way to a final answer. Chain of thought interpretability leverages these explanations to monito

We trained models to think in simpler, more traceable steps—so we can better understand how they work. ​​Neural networks power today’s most capable AI systems, but they remain difficult to understand. We don’t write these models with explicit, step-by-step instructions. Instead, they learn by adjusting billions of internal connections, or “weights,” until they master a task. We design the rules of training, but not the specific behaviors that emerge, and the result is a dense web of connections that no human can easily decipher. As AI systems become more capable and have real-world impact on d