© 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. 63604
    Prev
    Next
    INDEX
    Explanations

    file paths in code

    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
    .filter
    -0.08
     culminating
    -0.08
     verlie
    -0.08
     involves
    -0.07
    @Injectable
    -0.07
    larning
    -0.07
    ictions
    -0.07
     preocupación
    -0.07
     preocupação
    -0.07
     msn
    -0.07
    POSITIVE LOGITS
     위치
    0.10
    დებ
    0.10
    所在
    0.09
    (__
    0.09
     ഡയറ
    0.09
    .dirname
    0.08
     dirname
    0.08
     jiri
    0.08
     cwd
    0.08
    目录
    0.08
    Activations Density 0.005%

    No Known Activations