© 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. 11-RESID-POST-AA
    11. 7465
    Prev
    Next
    INDEX
    Explanations

    row

    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
    捕鱼
    -0.07
     players
    -0.07
     Mitarbeitern
    -0.07
    编辑
    -0.07
    -cut
    -0.07
     Hund
    -0.07
    .communication
    -0.07
     empleados
    -0.07
     Umsatz
    -0.07
    tà
    -0.07
    POSITIVE LOGITS
     لمح
    0.08
     [[[
    0.08
    Creates
    0.08
     ভিত
    0.08
     shading
    0.08
     সৃষ্টি
    0.07
     считается
    0.07
     принадлеж
    0.07
    opfu
    0.07
     originates
    0.07
    Activations Density 0.002%

    No Known Activations