© 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. 94491
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
     Hrvatske
    -0.09
     certamente
    -0.08
     shooters
    -0.08
    ŭ
    -0.08
     двум
    -0.08
     teamed
    -0.08
     Februar
    -0.08
     walk
    -0.07
    YLE
    -0.07
    manes
    -0.07
    POSITIVE LOGITS
     excessive
    0.09
    bidden
    0.08
     слово
    0.08
     hic
    0.07
     топ
    0.07
     overt
    0.07
     vaso
    0.07
    ;//
    0.07
     exces
    0.07
     dibujo
    0.07
    Activations Density 0.008%

    No Known Activations