© 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. 51394
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
     тоб
    -0.08
    Theo
    -0.07
    st
    -0.07
     koń
    -0.07
     sets
    -0.07
     встанов
    -0.07
     конца
    -0.07
    _tp
    -0.07
     Pastor
    -0.07
     паст
    -0.07
    POSITIVE LOGITS
     viktigt
    0.09
    ينة
    0.08
    ეული
    0.08
     medische
    0.08
     trag
    0.08
    ermi
    0.08
    chenke
    0.08
     preky
    0.08
    ിച്ചത്
    0.08
    əcək
    0.08
    Activations Density 0.000%

    No Known Activations