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. 30664
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
     Hodg
    -0.09
     hookup
    -0.08
     HOA
    -0.08
     hod
    -0.08
     kodi
    -0.08
    ↵				↵
    -0.08
     Martins
    -0.08
     संक्रम
    -0.08
     Rutherford
    -0.08
    mozilla
    -0.08
    POSITIVE LOGITS
     jie
    0.13
     Chinese
    0.12
    jiang
    0.12
     中国
    0.12
     Jian
    0.12
     Jie
    0.12
     yuan
    0.11
    ,中国
    0.11
    :中国
    0.11
     Zhong
    0.11
    Activations Density 0.062%

    No Known Activations