© 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. 54885
    Prev
    Next
    INDEX
    Explanations

    SQL queries and data manipulation

    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
     adanya
    -0.08
     recomiendo
    -0.08
     overheating
    -0.08
     Hell
    -0.08
    -0.08
    pertise
    -0.08
     આસ
    -0.07
     instinct
    -0.07
     agony
    -0.07
     Hvis
    -0.07
    POSITIVE LOGITS
     concat
    0.10
     UNION
    0.10
    concat
    0.10
    .concatenate
    0.10
     объедин
    0.10
    _union
    0.10
    combined
    0.10
     union
    0.10
    Combined
    0.10
     merged
    0.09
    Activations Density 0.011%
    No Known Activations