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. 11-RESID-POST-AA
    6. 11920
    Prev
    Next
    INDEX
    Explanations

    comprehensive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    例如
    -0.08
    硬
    -0.08
    不存在
    -0.08
    .“
    -0.08
    例えば
    -0.08
    。(
    -0.08
    如
    -0.08
    ,例如
    -0.08
    戏
    -0.08
     Mercer
    -0.07
    POSITIVE LOGITS
     خطة
    0.10
     подроб
    0.10
     подробно
    0.09
     summarizes
    0.08
     жосп
    0.08
     план
    0.08
     വിശദ
    0.08
     বিস্তারিত
    0.08
     quality
    0.08
     déta
    0.08
    Activations Density 0.013%

    No Known Activations