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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 65722
    Prev
    Next
    INDEX
    Explanations

    based

    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
     словам
    -0.08
     Shakespeare
    -0.08
     poign
    -0.08
     সাহিত্য
    -0.07
     Poet
    -0.07
     DOUBLE
    -0.07
    744
    -0.07
     영상
    -0.07
     자료
    -0.07
    _BUFFER
    -0.07
    POSITIVE LOGITS
    isiwa
    0.09
    ב
    0.09
     colored
    0.08
    înes
    0.08
     piyas
    0.08
     igualdad
    0.08
    opolis
    0.08
    Colored
    0.08
    ის
    0.08
     arena
    0.08
    Activations Density 0.003%

    No Known Activations