© 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. 3-RESID-POST-AA
    11. 1276
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    就是说
    -0.09
    Lo
    -0.08
     Silverado
    -0.08
    好了
    -0.08
     AGO
    -0.08
     Armada
    -0.08
    Kon
    -0.08
    dispatcher
    -0.07
     Burl
    -0.07
     escorts
    -0.07
    POSITIVE LOGITS
     lists
    0.07
     somewhere
    0.07
     sens
    0.07
    ount
    0.07
    刻
    0.07
     limit
    0.07
     Versch
    0.07
     умень
    0.07
     swollen
    0.07
     отдель
    0.07
    Activations Density 0.018%

    No Known Activations