© 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. 18925
    Prev
    Next
    INDEX
    Explanations

    Math/logic problems

    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
    unknown
    -0.10
    Some
    -0.10
     काही
    -0.10
     några
    -0.10
     कुछ
    -0.10
     hoffen
    -0.09
     Some
    -0.09
     algum
    -0.09
     Alguns
    -0.09
     some
    -0.09
    POSITIVE LOGITS
     daycare
    0.09
    ейств
    0.09
     trays
    0.09
    itaire
    0.08
     ميز
    0.08
    _inventory
    0.08
     مجموعه
    0.08
    总站
    0.08
     theatre
    0.08
     казино
    0.08
    Activations Density 0.026%

    No Known Activations