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. 77205
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     respons
    -0.08
     مث
    -0.08
     integrated
    -0.07
    responsive
    -0.07
     responsive
    -0.07
     sere
    -0.07
     reassuring
    -0.07
    sce
    -0.07
     recession
    -0.07
    atile
    -0.07
    POSITIVE LOGITS
     Parses
    0.09
     rashin
    0.09
     vict
    0.08
     verhind
    0.08
     qeyd
    0.08
     beperken
    0.08
     приема
    0.08
    න්ද
    0.08
    ücksicht
    0.08
     connector
    0.08
    Activations Density 0.002%

    No Known Activations