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. 30697
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     perdagangan
    -0.09
    .transactions
    -0.09
     publicar
    -0.08
    .publish
    -0.08
    购物
    -0.08
    所谓
    -0.08
    套利
    -0.08
    (delta
    -0.08
     Broadband
    -0.08
    手续费
    -0.08
    POSITIVE LOGITS
     prénom
    0.15
    Surname
    0.13
     surname
    0.13
    名字
    0.13
    姓名
    0.12
    surname
    0.12
     surn
    0.12
    姓
    0.11
     gender
    0.11
     names
    0.11
    Activations Density 0.043%

    No Known Activations