Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97066
    Prev
    Next
    INDEX
    Explanations

    Non-English 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
    öhn
    -0.08
    adó
    -0.08
    리고
    -0.08
    hout
    -0.08
    uant
    -0.08
    ogne
    -0.08
    adzi
    -0.08
    adz
    -0.08
    ondon
    -0.08
    hait
    -0.08
    POSITIVE LOGITS
    ಸ್ಥ
    0.08
    طرح
    0.08
    سب
    0.08
    سا
    0.07
     Cara
    0.07
    ೇಕ
    0.07
     Naughty
    0.07
    _NATIVE
    0.07
     شا
    0.07
    EF
    0.07
    Activations Density 0.000%

    No Known Activations