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. 130069
    Prev
    Next
    INDEX
    Explanations

    period

    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
    Fare
    -0.09
    accord
    -0.08
     évolution
    -0.08
     üle
    -0.08
     Exxon
    -0.08
     이는
    -0.07
     élect
    -0.07
     아직
    -0.07
     금융
    -0.07
    ."</
    -0.07
    POSITIVE LOGITS
     puesta
    0.08
     tqdm
    0.07
    _nums
    0.07
     excessive
    0.07
     zvin
    0.07
    følgelig
    0.07
    ,仅
    0.07
    plicht
    0.07
    ताल
    0.07
    ख्या
    0.07
    Activations Density 0.007%

    No Known Activations