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. 27197
    Prev
    Next
    INDEX
    Explanations

    dots

    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
     rebel
    -0.08
    ;-
    -0.07
     exercising
    -0.07
     homicide
    -0.07
    bitcoin
    -0.07
    ;
    -0.07
     bitcoin
    -0.07
     元
    -0.07
     ethic
    -0.07
     вул
    -0.07
    POSITIVE LOGITS
     creamy
    0.09
     luxurious
    0.08
     financement
    0.08
     floating
    0.08
    售价
    0.08
    0.08
     floats
    0.08
     spac
    0.08
     FLOAT
    0.07
     tinta
    0.07
    Activations Density 0.018%

    No Known Activations