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. 130919
    Prev
    Next
    INDEX
    Explanations

    unspoiled places

    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
    分
    -0.07
    编
    -0.07
    -d
    -0.07
    Mostly
    -0.07
    unehmen
    -0.07
    ujos
    -0.07
     Burma
    -0.07
    નમાં
    -0.07
    iscos
    -0.07
     分
    -0.07
    POSITIVE LOGITS
     magaca
    0.09
     namn
    0.08
    ديقة
    0.08
    {Name
    0.07
     tq
    0.07
     floral
    0.07
    َق
    0.07
     Pd
    0.07
     Bb
    0.07
     alguna
    0.07
    Activations Density 0.001%

    No Known Activations