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. 59962
    Prev
    Next
    INDEX
    Explanations

    ancient Chinese dynasties

    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
    Exif
    -0.09
     Sergio
    -0.09
     KDE
    -0.09
     Mell
    -0.09
    Č
    -0.08
     itk
    -0.08
     zau
    -0.08
    _percentage
    -0.08
     Marbella
    -0.08
     gtk
    -0.08
    POSITIVE LOGITS
    政治
    0.09
     political
    0.09
     রাজনৈতিক
    0.09
    发展
    0.09
     Burial
    0.09
    �
    0.09
    祭
    0.09
     રાજ
    0.08
     정치
    0.08
     burial
    0.08
    Activations Density 0.013%

    No Known Activations