© 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. 75686
    Prev
    Next
    INDEX
    Explanations

    art history

    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
     intelect
    -0.09
     Wrest
    -0.09
     intelectual
    -0.08
    گي
    -0.08
     intellectually
    -0.08
     Intellectual
    -0.08
     intellectual
    -0.08
     administer
    -0.08
    藝
    -0.08
     Arts
    -0.08
    POSITIVE LOGITS
     settlers
    0.09
     прогул
    0.09
     colonial
    0.08
     брать
    0.08
     mobile
    0.08
     plein
    0.08
     painters
    0.08
    Mobile
    0.08
     MLS
    0.08
     сня
    0.08
    Activations Density 0.012%

    No Known Activations