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. 44044
    Prev
    Next
    INDEX
    Explanations

    50

    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
    appings
    -0.08
    rocket
    -0.08
    (click
    -0.07
     matrimon
    -0.07
     küçük
    -0.07
     فيما
    -0.07
    andom
    -0.07
     ведущ
    -0.07
    大胆
    -0.07
     stratégies
    -0.07
    POSITIVE LOGITS
    岁
    0.08
     voorkeur
    0.08
     GN
    0.08
     Tomb
    0.08
    _TRACK
    0.08
    תי
    0.08
    GI
    0.08
    ================================================================================================
    0.07
    ofen
    0.07
    TRACK
    0.07
    Activations Density 0.001%

    No Known Activations