© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47604
    Prev
    Next
    INDEX
    Explanations

    etymology

    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
     bash
    -0.08
    液
    -0.08
     düzgün
    -0.08
     equiv
    -0.07
    028
    -0.07
     noto
    -0.07
     mica
    -0.07
     perusahaan
    -0.07
    MH
    -0.07
     dager
    -0.07
    POSITIVE LOGITS
    walo
    0.08
     इंटरनेट
    0.08
    ľa
    0.08
    áng
    0.08
    ótt
    0.08
     ऐप
    0.07
     Croix
    0.07
    apput
    0.07
     בלתי
    0.07
     гам
    0.07
    Activations Density 0.002%

    No Known Activations