© 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. 29697
    Prev
    Next
    INDEX
    Explanations

    param

    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
    导致
    -0.08
     Bistro
    -0.07
     antiqu
    -0.07
     olm
    -0.07
    非
    -0.07
     brillo
    -0.07
     boca
    -0.07
     non
    -0.07
    GUILayout
    -0.07
     XL
    -0.07
    POSITIVE LOGITS
    	Statement
    0.08
    	ws
    0.08
    (Start
    0.08
     vznik
    0.07
    (Resource
    0.07
     явно
    0.07
    byter
    0.07
    'w
    0.07
    เรา
    0.07
    	Resource
    0.07
    Activations Density 0.014%

    No Known Activations