© 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. 19-RESID-POST-AA
    11. 18671
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
     ...)
    -0.08
     uban
    -0.08
     dép
    -0.08
     ..."
    -0.08
    öhn
    -0.08
     ebenfalls
    -0.07
     meaningful
    -0.07
    mar
    -0.07
    would
    -0.07
    ++){
↵
    -0.07
    POSITIVE LOGITS
     Operating
    0.08
    них
    0.08
    Operating
    0.08
    одаря
    0.08
    ователь
    0.08
     operating
    0.08
    нили
    0.07
    ач
    0.07
    ичес
    0.07
    clusions
    0.07
    Activations Density 0.002%

    No Known Activations