© 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. 129432
    Prev
    Next
    INDEX
    Explanations

    signal

    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
    -rule
    -0.07
    林
    -0.07
    azier
    -0.07
    וה
    -0.07
    CLS
    -0.07
     afsl
    -0.07
    治
    -0.07
    itable
    -0.07
    ulte
    -0.07
     Schuld
    -0.07
    POSITIVE LOGITS
     provenant
    0.10
     fluctuations
    0.09
     приходит
    0.08
     distilled
    0.08
     atten
    0.08
     carrier
    0.08
     GREAT
    0.08
     সো
    0.08
    .interpolate
    0.08
    Кол
    0.08
    Activations Density 0.006%

    No Known Activations