© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68130
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     allocation
    -0.09
     eligible
    -0.09
     withholding
    -0.08
     stemmen
    -0.08
    赔
    -0.08
     awarding
    -0.08
     indemn
    -0.08
    Nonce
    -0.08
     Gewinner
    -0.08
     turnover
    -0.08
    POSITIVE LOGITS
     Transformation
    0.11
     transformation
    0.11
    Transformation
    0.11
     Transl
    0.10
     transform
    0.10
    转换
    0.10
     convert
    0.10
     translating
    0.10
     transforming
    0.10
     converting
    0.10
    Activations Density 0.031%

    No Known Activations