Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12761
    Prev
    Next
    INDEX
    Explanations

    about

    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
    ijat
    -0.08
    কর
    -0.08
    ಭ್ಯ
    -0.07
     deny
    -0.07
     Fred
    -0.07
     sit
    -0.07
    癌
    -0.07
     Carter
    -0.07
     Dyson
    -0.07
     desse
    -0.07
    POSITIVE LOGITS
    0.08
    tran
    0.08
     sput
    0.08
    king
    0.08
    alak
    0.08
    지
    0.07
    @property
    0.07
     Sap
    0.07
     сор
    0.07
     الأمر
    0.07
    Activations Density 0.006%

    No Known Activations