© 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. 70401
    Prev
    Next
    INDEX
    Explanations

    symmetry and rotation

    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
    ensk
    -0.08
     Rugby
    -0.07
    -0.07
    ücksicht
    -0.07
     मंगल
    -0.07
    Minecraft
    -0.07
     rarity
    -0.07
     Município
    -0.07
    centration
    -0.07
    avit
    -0.07
    POSITIVE LOGITS
    (hour
    0.08
    Petit
    0.08
     汉
    0.08
    0.08
    .hour
    0.08
    キング
    0.08
    汉
    0.08
     ami
    0.07
     Petit
    0.07
     clockwise
    0.07
    Activations Density 0.004%
    No Known Activations