© 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. 91364
    Prev
    Next
    INDEX
    Explanations

    exporting models

    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
     stationed
    -0.09
     driveway
    -0.09
    掲
    -0.08
     burglar
    -0.08
     Lotto
    -0.08
     lotto
    -0.08
    ியில்
    -0.08
     Waterloo
    -0.08
     CGPoint
    -0.08
    	background
    -0.08
    POSITIVE LOGITS
    .export
    0.13
    export
    0.11
    (export
    0.10
    _export
    0.10
    .dump
    0.10
    .serialize
    0.10
    .convert
    0.10
     export
    0.10
     exporter
    0.10
    冻结
    0.09
    Activations Density 0.003%

    No Known Activations