© 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. 18314
    Prev
    Next
    INDEX
    Explanations

    to

    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
     and
    -0.10
     மற்றும்
    -0.10
    "]=
    -0.09
    และ
    -0.09
     etc
    -0.09
    ;
    -0.09
    ;↵
    -0.09
    -even
    -0.09
     (`
    -0.09
     și
    -0.09
    POSITIVE LOGITS
     aquelas
    0.13
     aquellas
    0.12
     aqueles
    0.12
     hvernig
    0.12
     amikor
    0.11
     how
    0.11
     كيفية
    0.11
     aquellos
    0.10
     Certain
    0.10
     refers
    0.10
    Activations Density 0.090%

    No Known Activations