© 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. 1500
    Prev
    Next
    INDEX
    Explanations

    Czy

    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
     Colonial
    -0.09
     הח
    -0.08
     Tin
    -0.08
     Tha
    -0.08
     PTA
    -0.08
     Granite
    -0.08
     Brasileira
    -0.07
    ી�
    -0.07
     MHz
    -0.07
     SJ
    -0.07
    POSITIVE LOGITS
     incidence
    0.08
     constellation
    0.07
     incident
    0.07
     ist
    0.07
     инде
    0.07
    Plat
    0.07
    onnell
    0.07
     servo
    0.07
     suitability
    0.07
     سودا
    0.07
    Activations Density 0.000%

    No Known Activations