Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals

An activation oracle is a language model trained to read another model's internal activations and describe them in natural language, for example to name a secret word the other model was trained to hide. Oracle answers carry no measure of confidence, which limits their use in auditing. We compare five ways of attaching a confidence score to an oracle's answer on this secret-word task, across four oracles from two model families (Qwen and Gemma, 8B to 27B parameters), at 6{,}000 samples per method and oracle. The five methods rank the same way on all four oracles. Which method to use depends on one question: can the auditor list the possible answers in advance? If the auditor can, then having the oracle score each candidate answer roughly doubles accuracy and separates correct from wrong answers best of the five (AUROC 0.92 to 0.96). If the oracle must generate its answer freely and no labeled data exists, the agreement rate over twenty samples is the only confidence that is calibrated on every oracle. Once labeled data exists, a rescaled answer probability reaches the same calibration at one generation instead of twenty. Asking the oracle to state a confidence number gives no usable signal on any oracle. Code and the patched trainer are available at https://github.com/federicotorrielli/probabilistic_activation_oracles.