© 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. 18335
    Prev
    Next
    INDEX
    Explanations

    Circle direction

    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
     orgulho
    -0.09
    ↵↵　↵
    -0.09
     ivez
    -0.09
    म्भ
    -0.09
    ＠お腹いっぱい
    -0.09
     金叶
    -0.09
    <|reserved_200000|>
    -0.08
    қәа
    -0.08
     高登
    -0.08
    .എസ്
    -0.08
    POSITIVE LOGITS
     encountering
    0.10
     clockwise
    0.10
    方向
    0.10
    过程中
    0.10
     направлении
    0.10
     direction
    0.09
     hinweg
    0.09
     сторону
    0.09
     direção
    0.09
     Richtung
    0.09
    Activations Density 0.016%

    No Known Activations