© 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. 47096
    Prev
    Next
    INDEX
    Explanations

    reduce motion accessibility

    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
     бактер
    -0.07
     tổng
    -0.07
     đội
    -0.07
     bactér
    -0.07
     правиль
    -0.07
     Position
    -0.07
     Positions
    -0.07
    useq
    -0.07
    atius
    -0.07
     doğru
    -0.07
    POSITIVE LOGITS
     preferences
    0.09
     personalization
    0.09
    0.09
     disables
    0.09
    来了
    0.09
     disabling
    0.09
     anar
    0.08
    -disable
    0.08
     accommodations
    0.08
     Cran
    0.08
    Activations Density 0.004%
    No Known Activations