© 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. 47836
    Prev
    Next
    INDEX
    Explanations

    deal terms

    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
     Spinner
    -0.08
     autoridade
    -0.08
     divine
    -0.07
     Boat
    -0.07
     autoridad
    -0.07
     boat
    -0.07
    (Menu
    -0.07
     gezin
    -0.07
     homog
    -0.07
     இய
    -0.07
    POSITIVE LOGITS
    赔
    0.09
     지급
    0.09
    ồng
    0.08
    ùa
    0.08
     নগ
    0.08
    ită
    0.08
     бан
    0.08
    ുകയും
    0.08
    ไม่ต้องฝาก
    0.08
     clauses
    0.08
    Activations Density 0.081%

    No Known Activations