© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65514
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    onie
    -0.07
     boosts
    -0.07
     grâce
    -0.07
     pronto
    -0.07
    ich
    -0.07
    JSON
    -0.07
     ranking
    -0.07
     dzięki
    -0.07
    Quotes
    -0.07
    Arabic
    -0.07
    POSITIVE LOGITS
     是否
    0.13
    是否
    0.12
     apakah
    0.12
     여부
    0.12
     האם
    0.11
     feasibility
    0.11
    否
    0.11
    有没有
    0.10
     affirmative
    0.10
     نعم
    0.10
    Activations Density 0.052%

    No Known Activations