© 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. 22609
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .absolute
    -0.07
    .configure
    -0.06
    aculture
    -0.06
    .dto
    -0.06
     сня
    -0.06
     mande
    -0.06
     menjadi
    -0.06
     langkung
    -0.06
    开启
    -0.06
     полноцен
    -0.06
    POSITIVE LOGITS
    .find
    0.31
    找到
    0.30
     find
    0.30
     찾
    0.29
    寻找
    0.29
    find
    0.29
     찾아
    0.29
     найти
    0.28
    _find
    0.28
    Find
    0.28
    Activations Density 0.023%

    No Known Activations