© 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. 11-RESID-POST-AA
    11. 110623
    Prev
    Next
    INDEX
    Explanations

    pastry

    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
     rever
    -0.09
     tie
    -0.08
     Kiss
    -0.07
     Taste
    -0.07
    มาก
    -0.07
     Shed
    -0.07
     strongly
    -0.07
     زيادة
    -0.07
    К
    -0.07
     Solaris
    -0.07
    POSITIVE LOGITS
     awa
    0.08
     pât
    0.08
    .Decimal
    0.08
     fox
    0.08
    .Panel
    0.08
     lakh
    0.08
    ադր
    0.08
     thou
    0.08
     nais
    0.08
     pastry
    0.08
    Activations Density 0.004%

    No Known Activations