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. 98432
    Prev
    Next
    INDEX
    Explanations

    Asia

    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
     Hall
    -0.10
     Văn
    -0.10
     Zhang
    -0.08
    Hall
    -0.08
     Father
    -0.08
     Peu
    -0.08
     Huang
    -0.08
     Shenzhen
    -0.08
     Ville
    -0.08
     Jr
    -0.08
    POSITIVE LOGITS
    -亚洲
    0.16
    ეთის
    0.14
    大利
    0.14
    勒比
    0.12
    стандын
    0.12
    西亚
    0.12
    共和国
    0.12
    亚游
    0.12
    ეთში
    0.12
    尼斯人
    0.12
    Activations Density 0.008%

    No Known Activations