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. 130824
    Prev
    Next
    INDEX
    Explanations

    Russian language and шутливый

    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
    ивание
    -0.09
    даи
    -0.09
    ায়ী
    -0.09
     diving
    -0.08
     Dhabi
    -0.08
     PWM
    -0.08
    щее
    -0.08
     holding
    -0.08
    adav
    -0.08
    енными
    -0.08
    POSITIVE LOGITS
    ливо
    0.15
    лив
    0.13
    ли
    0.09
    лива
    0.09
    sters
    0.09
    оват
    0.09
    쟁
    0.09
    stories
    0.09
    monster
    0.08
    liwe
    0.08
    Activations Density 0.008%

    No Known Activations