© 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. 15-RESID-POST-AA
    11. 16646
    Prev
    Next
    INDEX
    Explanations

    simplified

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     βασ
    -0.08
     πολύ
    -0.08
    '");↵
    -0.08
     önemli
    -0.08
    instant
    -0.08
    rous
    -0.08
    >";↵
    -0.07
    ό
    -0.07
    ']];↵
    -0.07
    ">';↵
    -0.07
    POSITIVE LOGITS
     లేదు
    0.10
     नहीं
    0.08
     Packaging
    0.08
    _percentage
    0.08
    ിട്ടില്ല
    0.08
     नोट
    0.08
     formatting
    0.08
     eventueel
    0.08
     packaging
    0.08
     छैन
    0.08
    Activations Density 0.010%

    No Known Activations