© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49616
    Prev
    Next
    INDEX
    Explanations

    Russian names/politics

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     russian
    -0.14
     रूस
    -0.14
     الروسية
    -0.13
     روس
    -0.13
     russ
    -0.12
     russe
    -0.12
    Russian
    -0.12
     روسيا
    -0.11
     Russian
    -0.11
    俄
    -0.11
    POSITIVE LOGITS
     And
    0.15
     Py
    0.14
     M
    0.14
     Oleh
    0.13
     Berdimuhamed
    0.13
     Alla
    0.13
     Gr
    0.13
     Vy
    0.13
     Ev
    0.13
     Val
    0.13
    Activations Density 0.008%

    No Known Activations