© 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. 78781
    Prev
    Next
    INDEX
    Explanations

    amateur

    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
     Jinping
    -0.08
     Harrison
    -0.08
     Luxemburg
    -0.08
     Spine
    -0.07
     spine
    -0.07
    аха
    -0.07
     Qing
    -0.07
    awi
    -0.07
     Presid
    -0.07
    ующий
    -0.07
    POSITIVE LOGITS
    妙
    0.07
     Cartier
    0.07
    745
    0.07
    ish
    0.07
     worlds
    0.07
    (sz
    0.07
    748
    0.07
    版
    0.07
     wm
    0.07
     collectif
    0.07
    Activations Density 0.002%

    No Known Activations