© 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. 19-RESID-POST-AA
    11. 102838
    Prev
    Next
    INDEX
    Explanations

    visualization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="?
    -0.08
     ór
    -0.08
    ょう
    -0.07
    "errors
    -0.07
     thrift
    -0.07
    =(
    -0.07
     condolences
    -0.07
    =email
    -0.07
    Wunused
    -0.07
     restrictions
    -0.07
    POSITIVE LOGITS
     visualization
    0.35
     visualize
    0.33
    Visualization
    0.33
     visualizar
    0.33
     Visualization
    0.32
     imagining
    0.30
    visual
    0.29
     visual
    0.29
     envision
    0.28
    _visual
    0.28
    Activations Density 0.065%

    No Known Activations