© 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 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. 64223
    Prev
    Next
    INDEX
    Explanations

    Code and Chinese characters

    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
    同行
    -0.08
     različnih
    -0.08
    �
    -0.08
     geological
    -0.08
     CW
    -0.07
     verschillende
    -0.07
     واش
    -0.07
    人
    -0.07
     acuerdo
    -0.07
     人
    -0.07
    POSITIVE LOGITS
     unders
    0.08
    าจะ
    0.08
    eby
    0.08
     invas
    0.07
     hará
    0.07
    lem
    0.07
     שתי
    0.07
    _sales
    0.07
    0.07
     logarith
    0.07
    Activations Density 0.000%
    No Known Activations