© 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. 50345
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    -low
    -0.08
    -from
    -0.08
    -high
    -0.07
    -five
    -0.07
    -on
    -0.07
     sleep
    -0.07
    -fat
    -0.07
    ‌ر
    -0.07
    -of
    -0.07
    -four
    -0.07
    POSITIVE LOGITS
     Kreis
    0.08
     �
    0.08
    hiro
    0.08
    json
    0.08
    uiendo
    0.08
     vereador
    0.08
    ampler
    0.07
    året
    0.07
     collectibles
    0.07
    agira
    0.07
    Activations Density 0.001%

    No Known Activations