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. 54098
    Prev
    Next
    INDEX
    Explanations

    withholding

    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
     SWOT
    -0.09
     clay
    -0.09
     Clay
    -0.08
    vali
    -0.08
     sudoku
    -0.08
    Walls
    -0.08
    ød
    -0.08
     функцион
    -0.07
     chamber
    -0.07
     charcoal
    -0.07
    POSITIVE LOGITS
     지급
    0.10
     payroll
    0.10
     Payroll
    0.10
     выплаты
    0.09
     payouts
    0.09
    103
    0.09
     bookkeeping
    0.09
    支付
    0.09
     भुगतान
    0.09
    payment
    0.09
    Activations Density 0.008%

    No Known Activations