Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 112778
    Prev
    Next
    INDEX
    Explanations

    along

    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
    isms
    -0.09
    ism
    -0.08
    FETCH
    -0.08
    favor
    -0.08
    plants
    -0.07
    anns
    -0.07
    imax
    -0.07
    éri
    -0.07
    Favor
    -0.07
     warrant
    -0.07
    POSITIVE LOGITS
     شده
    0.09
     日
    0.08
     atas
    0.08
     Regular
    0.07
    ยัน
    0.07
     Рег
    0.07
    ಿಯಾದ
    0.07
     تسجيل
    0.07
     删除
    0.07
     Shen
    0.07
    Activations Density 0.000%

    No Known Activations