© 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. 24693
    Prev
    Next
    INDEX
    Explanations

    sobel edge detection

    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
     Billion
    -0.09
    _RE
    -0.08
    bags
    -0.08
    bag
    -0.08
    Bag
    -0.08
     bag
    -0.08
     встрет
    -0.08
    _re
    -0.08
    лек
    -0.08
     recol
    -0.08
    POSITIVE LOGITS
     derivative
    0.16
    Derivative
    0.14
     derivatives
    0.14
    ivative
    0.10
     detecting
    0.09
    curl
    0.09
     detects
    0.09
     extracting
    0.09
     gradients
    0.09
    .gradient
    0.09
    Activations Density 0.009%

    No Known Activations