© 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 EvalsExportsinterp-engineNEWAPI 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. 71101
    Prev
    Next
    INDEX
    Explanations

    a

    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
    _pro
    -0.08
    ələrin
    -0.07
    pro
    -0.07
     Concepts
    -0.07
    isele
    -0.07
    玲
    -0.07
    琪
    -0.07
     Leon
    -0.07
     вяд
    -0.07
     утверж
    -0.07
    POSITIVE LOGITS
     साझा
    0.14
     shared
    0.14
     gemeinsamen
    0.13
    Shared
    0.12
    共同
    0.11
    shared
    0.11
     مشتر
    0.11
     gemeinsame
    0.11
    .shared
    0.10
    ，共
    0.10
    Activations Density 0.088%

    No Known Activations