© 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. 23-RESID-POST-AA
    11. 48985
    Prev
    Next
    INDEX
    Explanations

    Veget

    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
    (QObject
    -0.08
    o
    -0.08
    ibri
    -0.08
     tentu
    -0.08
    thorn
    -0.08
     người
    -0.08
     выхода
    -0.08
     പരിശ
    -0.08
    igita
    -0.08
     વિષ
    -0.07
    POSITIVE LOGITS
    ables
    0.14
    ۱۰
    0.08
    ies
    0.08
     valuables
    0.08
     meats
    0.08
    gies
    0.08
     المواد
    0.08
    .Payment
    0.08
    ayment
    0.08
     proteins
    0.08
    Activations Density 0.001%

    No Known Activations