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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103452
    Prev
    Next
    INDEX
    Explanations

    commas/quotes

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     talvez
    -0.13
     quizás
    -0.13
    Perhaps
    -0.11
     posiblemente
    -0.11
    Vielleicht
    -0.11
     Vielleicht
    -0.11
     quizá
    -0.11
     Возможно
    -0.10
     vielleicht
    -0.10
     शायद
    -0.10
    POSITIVE LOGITS
     various
    0.09
     cloning
    0.08
     GPS
    0.08
     etc
    0.08
     many
    0.08
     както
    0.08
     brainstorming
    0.08
    ...',↵
    0.08
     AN
    0.08
    ":↵
    0.07
    Activations Density 0.032%

    No Known Activations