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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111431
    Prev
    Next
    INDEX
    Explanations

    ex

    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
     glaucoma
    -0.08
     Gross
    -0.08
    (JS
    -0.07
    (net
    -0.07
    cloth
    -0.07
    كه
    -0.07
     withstand
    -0.07
    alik
    -0.07
     Smaller
    -0.07
    Gross
    -0.07
    POSITIVE LOGITS
    omon
    0.08
    兄
    0.08
    宅
    0.08
    曰
    0.08
    Neighbors
    0.07
     arkadaş
    0.07
     Nicole
    0.07
    েরা
    0.07
    -element
    0.07
     элемента
    0.07
    Activations Density 0.007%

    No Known Activations