© 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. 21370
    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
     Bowie
    -0.07
     div
    -0.07
    enis
    -0.07
    ,^
    -0.07
    333
    -0.07
     Familia
    -0.07
     smooth
    -0.07
    _GL
    -0.06
     Duit
    -0.06
     disappointment
    -0.06
    POSITIVE LOGITS
    related
    0.11
    帮
    0.11
    قدمة
    0.11
    িজ্ঞ
    0.10
    相
    0.10
    قاذ
    0.10
    ադարձ
    0.10
    相关
    0.10
    عل
    0.09
    ազգային
    0.09
    Activations Density 0.001%

    No Known Activations