© 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. 47167
    Prev
    Next
    INDEX
    Explanations

    legislation and resolving differences

    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
     Gone
    -0.08
    ื่
    -0.08
    λιά
    -0.08
    ;margin
    -0.08
     aposent
    -0.08
    Nunca
    -0.08
    Gone
    -0.08
     वृद्ध
    -0.07
     contemporary
    -0.07
     décadas
    -0.07
    POSITIVE LOGITS
     combine
    0.10
    Combine
    0.10
    combine
    0.09
    merge
    0.09
     Combine
    0.09
    erging
    0.09
     aggregator
    0.08
     объедин
    0.08
     Combined
    0.08
    不同
    0.08
    Activations Density 0.022%

    No Known Activations