© 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. 108200
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations

    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
     lạnh
    -0.08
     tense
    -0.08
     ದು
    -0.08
     Eurovision
    -0.08
     pendiente
    -0.08
     năng
    -0.07
    ೀ
    -0.07
     ауа
    -0.07
     nucle
    -0.07
     cú
    -0.07
    POSITIVE LOGITS
     prosecut
    0.08
    FTC
    0.08
     도
    0.08
     Browse
    0.08
     sand
    0.08
    rash
    0.07
     Substance
    0.07
    .Enabled
    0.07
    -ft
    0.07
     Schwartz
    0.07
    Activations Density 0.036%

    No Known Activations