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. 11921
    Prev
    Next
    INDEX
    Explanations

    Numbers and sizes

    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
     гро
    -0.08
    _RESET
    -0.08
     resets
    -0.08
     Reset
    -0.08
     coupons
    -0.08
     Dream
    -0.08
     طبيعي
    -0.07
     Blues
    -0.07
     кампан
    -0.07
     הנ
    -0.07
    POSITIVE LOGITS
    大小
    0.09
    人数
    0.08
    Size
    0.08
    _size
    0.08
    씩
    0.08
    方法
    0.08
     आकार
    0.08
    サイズ
    0.08
     ukuran
    0.08
    यह
    0.08
    Activations Density 0.050%

    No Known Activations