© 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. 7823
    Prev
    Next
    INDEX
    Explanations

    math symbols

    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
     PPP
    -0.07
    גענ
    -0.07
     میان
    -0.07
    .Step
    -0.07
    zes
    -0.07
     UIWindow
    -0.07
    umma
    -0.07
     contracted
    -0.07
    ierende
    -0.07
     conglomer
    -0.07
    POSITIVE LOGITS
    头
    0.08
     yoki
    0.08
     või
    0.07
    或
    0.07
     veya
    0.07
    unds
    0.07
     किंवा
    0.07
    /header
    0.07
     première
    0.07
    UND
    0.07
    Activations Density 0.117%

    No Known Activations