© 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. 69928
    Prev
    Next
    INDEX
    Explanations

    limitation

    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
    먼
    -0.08
    отреб
    -0.08
    좀
    -0.08
     받아
    -0.07
     할
    -0.07
     한번
    -0.07
    몸
    -0.07
    Wilson
    -0.07
    TTL
    -0.07
    할
    -0.07
    POSITIVE LOGITS
    721
    0.08
     obligations
    0.08
     indemn
    0.08
     иму
    0.08
     vincul
    0.07
     गल
    0.07
     (...
    0.07
     NAT
    0.07
    332
    0.07
     Unless
    0.07
    Activations Density 0.002%

    No Known Activations