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. 11666
    Prev
    Next
    INDEX
    Explanations

    negation

    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
     implic
    -0.08
     -----
    -0.08
     λόγω
    -0.08
     asta
    -0.07
     بیشتری
    -0.07
     دقی
    -0.07
    ด้วย
    -0.07
     Aufgrund
    -0.07
     aufgrund
    -0.07
     Bor
    -0.07
    POSITIVE LOGITS
    CREEN
    0.08
     Expense
    0.07
     сч
    0.07
     мужч
    0.07
    Proper
    0.07
    -lived
    0.07
    安徽
    0.07
    	panic
    0.07
     pest
    0.07
     merry
    0.07
    Activations Density 0.027%

    No Known Activations