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

    Neuronpedia

    APICircuit 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. 106310
    Prev
    Next
    INDEX
    Explanations

    entry

    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
     schedule
    -0.08
     TON
    -0.08
     (?)
    -0.07
    овый
    -0.07
     STORIES
    -0.07
     })),↵
    -0.07
    (schedule
    -0.07
     clínica
    -0.07
     cerita
    -0.07
    ूर
    -0.07
    POSITIVE LOGITS
    >=
    0.08
    Internet
    0.07
    cheon
    0.07
    학
    0.07
     informa
    0.07
    opol
    0.07
     Savannah
    0.07
     greeted
    0.07
    onaise
    0.07
     Albuquerque
    0.07
    Activations Density 0.006%

    No Known Activations