© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18456
    Prev
    Next
    INDEX
    Explanations

    is

    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
     физических
    -0.08
     бетон
    -0.08
     физ
    -0.08
    REN
    -0.08
     бухгалтер
    -0.08
    caler
    -0.08
    .Excel
    -0.08
     "%.
    -0.08
    ecção
    -0.08
    cloud
    -0.08
    POSITIVE LOGITS
     odd
    0.36
    odd
    0.31
     Odd
    0.30
    Odd
    0.28
     奇
    0.20
    奇
    0.20
     odds
    0.19
     oddly
    0.18
     홀
    0.18
    Odds
    0.15
    Activations Density 0.141%

    No Known Activations