© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29241
    Prev
    Next
    INDEX
    Explanations

    announcements/notices

    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
    hsil
    -0.08
    eschool
    -0.07
    heo
    -0.07
    upr
    -0.07
     Eleven
    -0.07
    ლ
    -0.07
    dang
    -0.07
     UICollection
    -0.07
     sonuc
    -0.07
    ological
    -0.07
    POSITIVE LOGITS
     যারা
    0.08
     bicarbon
    0.08
     pois
    0.08
     //------------------------------------------------
    0.07
     assimil
    0.07
     reload
    0.07
     repression
    0.07
     తమ
    0.07
     kautta
    0.07
     tungsten
    0.07
    Activations Density 0.316%

    No Known Activations