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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19096
    Prev
    Next
    INDEX
    Explanations

    9

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -wide
    -0.07
     suo
    -0.07
     whole
    -0.07
     DIA
    -0.07
     Stateful
    -0.07
    绕
    -0.07
    .↵/
    -0.07
    angian
    -0.06
    _DI
    -0.06
     war
    -0.06
    POSITIVE LOGITS
     istifadə
    0.08
    ’utiliser
    0.08
     neke
    0.08
    Of
    0.08
    .อ
    0.08
     รีวิว
    0.08
    elif
    0.08
     acknowled
    0.08
    …)
    0.08
     แสดงความคิดเห็น
    0.08
    Activations Density 0.006%

    No Known Activations