© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48106
    Prev
    Next
    INDEX
    Explanations

    data analysis and predictions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .json
    -0.09
    _json
    -0.09
    /json
    -0.09
    =json
    -0.08
     JSON
    -0.08
    (JSON
    -0.08
    _JSON
    -0.08
    -json
    -0.08
    json
    -0.08
    JSON
    -0.08
    POSITIVE LOGITS
     taxi
    0.11
     flights
    0.10
     petrol
    0.10
    Taxi
    0.10
     foot
    0.10
     cellphone
    0.10
     Petrol
    0.10
     electricity
    0.10
     Flights
    0.10
     Google
    0.10
    Activations Density 0.006%

    No Known Activations