© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47973
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hete
    -0.08
     vooruit
    -0.08
    $/,↵
    -0.08
    няется
    -0.08
    terie
    -0.08
    وه
    -0.08
     Bowie
    -0.08
    ndares
    -0.07
     جائے
    -0.07
     vas
    -0.07
    POSITIVE LOGITS
     фото
    0.08
     ardu
    0.07
    Orbit
    0.07
     timeframe
    0.07
    _ul
    0.07
     Orbit
    0.07
     wers
    0.07
     competition
    0.07
    Intensity
    0.07
     storico
    0.07
    Activations Density 0.008%

    No Known Activations