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. 12252
    Prev
    Next
    INDEX
    Explanations

    numerology and personality

    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
    .bool
    -0.08
    掲載
    -0.08
    *sizeof
    -0.08
    Meth
    -0.08
    .eval
    -0.07
     אפשר
    -0.07
     удоб
    -0.07
     sexist
    -0.07
     selber
    -0.07
    ník
    -0.07
    POSITIVE LOGITS
     chosen
    0.09
    legacy
    0.08
     escolhido
    0.08
    Legacy
    0.08
     chois
    0.08
     legacy
    0.07
     Legacy
    0.07
    Chosen
    0.07
    chosen
    0.07
     weich
    0.07
    Activations Density 0.005%

    No Known Activations