© 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. 75664
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ystème
    -0.08
     kisses
    -0.08
     já
    -0.08
     condensation
    -0.07
    .Serialization
    -0.07
     traversal
    -0.07
    נג
    -0.07
     roommates
    -0.07
     kamers
    -0.07
    kau
    -0.07
    POSITIVE LOGITS
     manual
    0.17
     Manual
    0.17
    Manual
    0.16
    manual
    0.16
    _manual
    0.15
     вруч
    0.14
    .manual
    0.14
     mensch
    0.13
     মানব
    0.13
     human
    0.13
    Activations Density 0.036%

    No Known Activations