© 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. 24838
    Prev
    Next
    INDEX
    Explanations

    ou

    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
     razor
    -0.08
     digestive
    -0.08
     والس
    -0.07
     زر
    -0.07
     Diario
    -0.07
     رح
    -0.07
     Diary
    -0.07
     القرن
    -0.07
     miles
    -0.07
     السيد
    -0.07
    POSITIVE LOGITS
    LW
    0.08
    .separator
    0.08
    .rating
    0.08
    }↵↵↵
    0.08
    /error
    0.07
    /messages
    0.07
     loudly
    0.07
     الو
    0.07
     parap
    0.07
    .Error
    0.07
    Activations Density 0.074%

    No Known Activations