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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 51839
    Prev
    Next
    INDEX
    Explanations

    South American civilizations

    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
    .Ad
    -0.08
     pm
    -0.08
    .adjust
    -0.08
     नस
    -0.08
     ночью
    -0.07
     tox
    -0.07
     mafi
    -0.07
     domic
    -0.07
    .disconnect
    -0.07
    .atan
    -0.07
    POSITIVE LOGITS
     extensively
    0.08
    Cool
    0.08
     കീ
    0.08
    agé
    0.07
     പരീക്ഷ
    0.07
    india
    0.07
    μή
    0.07
    ema
    0.07
    Stuff
    0.07
     trailers
    0.07
    Activations Density 0.000%

    No Known Activations