© 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. 23-RESID-POST-AA
    11. 50588
    Prev
    Next
    INDEX
    Explanations

    Mixed foreign language, symbols

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     P
    -0.09
     Sof
    -0.08
     Es
    -0.08
     Poul
    -0.07
     pule
    -0.07
     th
    -0.07
     qul
    -0.07
     Trim
    -0.07
     p
    -0.07
    p
    -0.07
    POSITIVE LOGITS
    ਐ
    0.08
    ਏ
    0.08
    ਾਇ
    0.08
    ഐ
    0.07
    .OP
    0.07
    Ｏ
    0.07
    ਬ
    0.07
    бас
    0.07
    ਡ
    0.07
     ਵ
    0.07
    Activations Density 0.053%

    No Known Activations