© 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. 111088
    Prev
    Next
    INDEX
    Explanations

    重点

    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
     complic
    -0.08
    ろ
    -0.08
     obligated
    -0.08
    -ф
    -0.08
     bliss
    -0.08
     велич
    -0.08
    സ
    -0.07
     praat
    -0.07
    ுவத
    -0.07
     betrokken
    -0.07
    POSITIVE LOGITS
    areas
    0.09
    områ
    0.09
    とな
    0.09
     areas
    0.08
     !!!
    0.08
    之一
    0.08
    重点
    0.08
     områder
    0.08
    setzung
    0.08
     bagi
    0.08
    Activations Density 0.012%

    No Known Activations