© 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. 7-RESID-POST-AA
    11. 1397
    Prev
    Next
    INDEX
    Explanations

    popup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maneuver
    -0.08
    -danger
    -0.08
    danger
    -0.08
    hits
    -0.08
    Held
    -0.07
    Recursive
    -0.07
    hina
    -0.07
    Objective
    -0.07
    ances
    -0.07
     polarity
    -0.07
    POSITIVE LOGITS
    贵
    0.08
    按钮
    0.08
     ANI
    0.08
     κ
    0.07
     Automobile
    0.07
     ønsker
    0.07
     পাশে
    0.07
    等待
    0.07
    0.07
    快
    0.07
    Activations Density 0.001%
    No Known Activations