© 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. 47969
    Prev
    Next
    INDEX
    Explanations

    fract

    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
    ränkt
    -0.08
    込
    -0.08
     Kenn
    -0.08
    做
    -0.07
     anthrop
    -0.07
     unkompl
    -0.07
    ='')↵
    -0.07
     umuk
    -0.07
    (rs
    -0.07
     lass
    -0.07
    POSITIVE LOGITS
     fract
    0.09
    patterns
    0.09
    Patterns
    0.09
    -pattern
    0.09
     suns
    0.08
     पर्व
    0.08
    .tree
    0.08
    .pattern
    0.08
     Von
    0.08
     प्र
    0.08
    Activations Density 0.002%

    No Known Activations