© 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. 63280
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    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
     enkl
    -0.08
    简单
    -0.08
     scarce
    -0.08
     tenu
    -0.08
     CSC
    -0.07
     cleaner
    -0.07
    쉽
    -0.07
     simpler
    -0.07
     easier
    -0.07
     risco
    -0.07
    POSITIVE LOGITS
     подробно
    0.15
     déta
    0.14
     подроб
    0.14
     uitgebreide
    0.14
     umfang
    0.14
     التفاصيل
    0.13
     thorough
    0.13
     detaill
    0.13
     Detailed
    0.13
     વિગ
    0.12
    Activations Density 0.144%

    No Known Activations