© 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. 95365
    Prev
    Next
    INDEX
    Explanations

    Historical fiction/accounts

    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
     typing
    -0.09
    Typing
    -0.09
     peek
    -0.09
     elast
    -0.09
     HOA
    -0.09
    typing
    -0.08
     שלי
    -0.08
     subcon
    -0.08
     sensory
    -0.08
     Elast
    -0.08
    POSITIVE LOGITS
     political
    0.15
    政治
    0.15
     정치
    0.14
     রাজনৈতিক
    0.14
     propaganda
    0.13
     politically
    0.13
     राजनीतिक
    0.13
     nationalist
    0.12
     రాజకీయ
    0.12
    polit
    0.12
    Activations Density 0.019%

    No Known Activations