© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77840
    Prev
    Next
    INDEX
    Explanations

    [player

    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
     Declar
    -0.08
     horiz
    -0.07
     horizontal
    -0.07
     stream
    -0.07
     matur
    -0.07
     Höhen
    -0.07
     inclusion
    -0.07
     lina
    -0.07
    Horizontal
    -0.06
     declar
    -0.06
    POSITIVE LOGITS
    וכל
    0.08
     इलेक्ट्र
    0.08
     электр
    0.08
    에게
    0.08
    俄
    0.08
     মারা
    0.08
     элект
    0.08
     electricians
    0.08
    казать
    0.08
    angnya
    0.08
    Activations Density 0.007%

    No Known Activations