© 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. 70050
    Prev
    Next
    INDEX
    Explanations

    ability

    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
     glic
    -0.08
    患
    -0.08
     patio
    -0.08
     Sessions
    -0.08
     parking
    -0.08
    ETING
    -0.07
    aments
    -0.07
    zení
    -0.07
     ounces
    -0.07
    اص
    -0.07
    POSITIVE LOGITS
    esc
    0.09
     predictable
    0.09
     מראש
    0.09
     attentes
    0.09
     verwachting
    0.08
    期待
    0.08
     anticipation
    0.08
     Erwartungen
    0.08
     expectativas
    0.08
     EXPECT
    0.08
    Activations Density 0.009%

    No Known Activations