© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 69013
    Prev
    Next
    INDEX
    Explanations

    of

    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
    -example
    -0.07
    啊
    -0.07
     innovations
    -0.07
     отличие
    -0.07
     cybersecurity
    -0.07
    (example
    -0.07
     себеп
    -0.07
     economists
    -0.07
    실
    -0.07
    ,q
    -0.07
    POSITIVE LOGITS
     relying
    0.09
     genus
    0.08
     Μα
    0.08
     weg
    0.08
     focusing
    0.07
    جون
    0.07
     just
    0.07
     rely
    0.07
     Бар
    0.07
     tantos
    0.07
    Activations Density 0.021%

    No Known Activations