© 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. 70862
    Prev
    Next
    INDEX
    Explanations

    ّ

    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
     Ket
    -0.08
    Ket
    -0.08
    Cooling
    -0.07
    nal
    -0.07
    .FC
    -0.07
     Bra
    -0.07
     Cooling
    -0.07
     sloppy
    -0.07
    빈
    -0.07
    BRA
    -0.07
    POSITIVE LOGITS
    gharị
    0.08
    展
    0.08
    悟
    0.08
    யம்
    0.07
     Aleks
    0.07
    نين
    0.07
     تس
    0.07
     Yah
    0.07
    Poi
    0.07
    pụta
    0.07
    Activations Density 0.086%

    No Known Activations