© 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. 31550
    Prev
    Next
    INDEX
    Explanations

    math/inequality

    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
     Schre
    -0.08
    .iter
    -0.08
     Ingredient
    -0.07
     Joseph
    -0.07
     gaat
    -0.07
    .io
    -0.07
    .Consumer
    -0.07
     aliment
    -0.07
     nurturing
    -0.07
     nutritious
    -0.07
    POSITIVE LOGITS
    、不
    0.09
     وعدم
    0.09
     discrep
    0.08
    عدم
    0.08
    異
    0.08
     distorted
    0.08
     बल्कि
    0.08
    ,T
    0.08
     forged
    0.08
     differing
    0.08
    Activations Density 0.037%

    No Known Activations