© 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. 70684
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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
     incentives
    -0.08
    actors
    -0.08
    integr
    -0.08
    bonus
    -0.08
    .styles
    -0.08
    anguard
    -0.08
    ionista
    -0.08
    never
    -0.08
    ilece
    -0.08
    ipelago
    -0.08
    POSITIVE LOGITS
     OE
    0.09
     Proceedings
    0.08
     SO
    0.08
     Papers
    0.08
     CMP
    0.07
     ఆయన
    0.07
    -Term
    0.07
     ABOUT
    0.07
     cuire
    0.07
    ائرة
    0.07
    Activations Density 0.003%

    No Known Activations