© 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. 1006
    Prev
    Next
    INDEX
    Explanations

    v

    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
     anemia
    -0.09
     Organized
    -0.08
     Femin
    -0.08
     clasificación
    -0.08
     departmental
    -0.08
     whakamah
    -0.08
     coordinación
    -0.08
     estructura
    -0.08
     whakar
    -0.08
     Developed
    -0.08
    POSITIVE LOGITS
    ில்ல
    0.10
    ில
    0.09
    ில்லை
    0.08
    =$
    0.07
    _query
    0.07
    ']."</
    0.07
     попробовать
    0.07
    $query
    0.07
    /query
    0.07
     proportional
    0.07
    Activations Density 0.003%

    No Known Activations