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. 12802
    Prev
    Next
    INDEX
    Explanations

    historical

    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
     fluores
    -0.08
     turista
    -0.08
    ored
    -0.07
    structures
    -0.07
    itone
    -0.07
    nata
    -0.07
     fridge
    -0.07
    处分
    -0.07
     alcool
    -0.07
     électron
    -0.07
    POSITIVE LOGITS
    历史
    0.10
     history
    0.10
    歷
    0.09
     ചരിത്ര
    0.09
     History
    0.09
     Merc
    0.09
    history
    0.09
     evolution
    0.09
     Evolution
    0.09
     geschiedenis
    0.09
    Activations Density 0.006%

    No Known Activations