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. 30658
    Prev
    Next
    INDEX
    Explanations

    -check

    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
     endeavors
    -0.08
    ението
    -0.08
     tập
    -0.07
     WH
    -0.07
    wetten
    -0.07
    -songwriter
    -0.07
    든
    -0.07
     объедин
    -0.07
     hopes
    -0.07
     bán
    -0.07
    POSITIVE LOGITS
     tentang
    0.09
     wording
    0.08
    关于
    0.08
     mengenai
    0.08
    About
    0.08
     بشأن
    0.07
     About
    0.07
    Sobre
    0.07
    เกี่ยว
    0.07
     revise
    0.07
    Activations Density 0.014%

    No Known Activations