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. 103177
    Prev
    Next
    INDEX
    Explanations

    Name

    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
    густ
    -0.09
    ندان
    -0.08
     shelves
    -0.08
     newline
    -0.08
     натураль
    -0.08
     slash
    -0.08
     points
    -0.08
    slash
    -0.08
     nước
    -0.08
    -flow
    -0.07
    POSITIVE LOGITS
     titulo
    0.09
    (title
    0.09
     nameof
    0.09
     Title
    0.09
     Monitoring
    0.09
    	title
    0.09
    此次
    0.08
     title
    0.08
     Male
    0.08
     titled
    0.08
    Activations Density 0.001%

    No Known Activations