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. 113078
    Prev
    Next
    INDEX
    Explanations

    seals

    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
     sadd
    -0.08
    decltype
    -0.07
     aproxim
    -0.07
    晰
    -0.07
    用户
    -0.07
    语言
    -0.07
    提供
    -0.07
    情侣
    -0.07
    vl
    -0.07
    rachen
    -0.07
    POSITIVE LOGITS
    হন
    0.08
     निम
    0.08
     profesión
    0.08
     гум
    0.08
     professionelle
    0.08
     profession
    0.08
     deskund
    0.08
     Fiesta
    0.07
    ievable
    0.07
     деле
    0.07
    Activations Density 0.000%

    No Known Activations