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. 9121
    Prev
    Next
    INDEX
    Explanations

    recipe quantities

    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
    恋
    -0.08
     beliebtesten
    -0.07
     appraisal
    -0.07
     inflated
    -0.07
    flatten
    -0.07
     FTP
    -0.07
     prey
    -0.07
    群众
    -0.07
    /octet
    -0.07
    人気
    -0.07
    POSITIVE LOGITS
     teaspoons
    0.12
     teaspoon
    0.12
     doses
    0.10
     tiny
    0.10
     tablespoon
    0.10
     dosing
    0.09
     miniature
    0.09
     negligible
    0.09
    tiny
    0.09
     صغيرة
    0.09
    Activations Density 0.014%

    No Known Activations