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. 98371
    Prev
    Next
    INDEX
    Explanations

    seasonal variations

    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
    天
    -0.09
     九
    -0.08
    را
    -0.08
     面
    -0.08
     bijeen
    -0.08
     Santa
    -0.07
     detail
    -0.07
     Si
    -0.07
     Padre
    -0.07
    تمام
    -0.07
    POSITIVE LOGITS
     chuyển
    0.11
    轉
    0.11
    动
    0.11
    動
    0.10
    转
    0.10
     zool
    0.10
    动物
    0.09
     動
    0.09
    转载
    0.09
     动
    0.09
    Activations Density 0.004%

    No Known Activations