© 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. 19-RESID-POST-AA
    11. 19082
    Prev
    Next
    INDEX
    Explanations

    "or" in different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     йый
    -0.09
     Daarmee
    -0.09
     қатарлиқ
    -0.09
    utinut
    -0.09
    imasut
    -0.09
    ulluunniit
    -0.09
    lugit
    -0.09
    utinik
    -0.09
    atsinni
    -0.09
    лиридин
    -0.08
    POSITIVE LOGITS
     அல்லது
    0.14
     ಅಥವಾ
    0.13
     or
    0.12
    或
    0.12
     hoặc
    0.12
     மற்றும்
    0.12
     oder
    0.11
     ಮತ್ತು
    0.11
     或
    0.11
    ,G
    0.11
    Activations Density 0.067%

    No Known Activations