© 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. 108169
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     braces
    -0.08
     incompetent
    -0.07
    -0.07
    弊
    -0.07
    Conclus
    -0.07
    іж
    -0.07
    árm
    -0.07
    Br
    -0.07
    ాస
    -0.07
    ۈر
    -0.07
    POSITIVE LOGITS
    ”
    0.08
     ಸಾಗ
    0.08
     slate
    0.07
     '''↵↵
    0.07
     abase
    0.07
    ,''
    0.07
    .trans
    0.07
    /trans
    0.07
     pname
    0.07
     merkt
    0.07
    Activations Density 0.009%
    No Known Activations