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. 111884
    Prev
    Next
    INDEX
    Explanations

    Code generation

    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
     trustworthy
    -0.08
     contradict
    -0.07
     mutation
    -0.07
     Mutation
    -0.07
    Mutation
    -0.07
    itores
    -0.07
    ertools
    -0.07
    forget
    -0.07
     certe
    -0.07
     pam
    -0.07
    POSITIVE LOGITS
    北京时间
    0.08
     veter
    0.08
     Maks
    0.08
    0.08
    [_
    0.08
     Bowling
    0.08
    раль
    0.08
     procès
    0.07
    ालन
    0.07
    “What
    0.07
    Activations Density 0.000%

    No Known Activations