© 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. 70901
    Prev
    Next
    INDEX
    Explanations

    structure infrastructure

    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
     emailing
    -0.08
     pedi
    -0.08
     округ
    -0.08
     Ranger
    -0.08
     Parmesan
    -0.08
     حساب
    -0.08
     CONCAT
    -0.08
     Compound
    -0.08
     exklus
    -0.08
     XC
    -0.07
    POSITIVE LOGITS
    塑
    0.10
    heard
    0.09
     entw
    0.08
     영향을
    0.08
    ale
    0.08
    影响
    0.08
     intangible
    0.08
     beeinfl
    0.08
     techno
    0.08
    Religion
    0.08
    Activations Density 0.052%

    No Known Activations