© 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. 95277
    Prev
    Next
    INDEX
    Explanations

    mouth/wind instrument sound production

    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
     walks
    -0.08
     books
    -0.08
     Yuk
    -0.08
    Snapshots
    -0.08
     databases
    -0.08
     walking
    -0.08
     walkers
    -0.08
     journeys
    -0.08
     decentral
    -0.07
     snapshots
    -0.07
    POSITIVE LOGITS
     toothpaste
    0.08
    刷
    0.08
     pâte
    0.08
    _Buffer
    0.08
     đọc
    0.08
    ococcus
    0.08
     Vocal
    0.08
    iqu
    0.08
     shin
    0.08
    对刷
    0.07
    Activations Density 0.009%

    No Known Activations