© 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. 23-RESID-POST-AA
    11. 50990
    Prev
    Next
    INDEX
    Explanations

    russian education words

    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
     Gotham
    -0.09
    otland
    -0.09
     Austral
    -0.09
     COUR
    -0.09
    袭
    -0.08
    ойчив
    -0.08
     Crus
    -0.08
     Brexit
    -0.08
     Court
    -0.08
     bewijs
    -0.08
    POSITIVE LOGITS
     воспит
    0.12
     wych
    0.11
     παι
    0.11
     дош
    0.10
     педагог
    0.10
     odborn
    0.10
     pedagog
    0.09
     cadres
    0.09
     craftsmen
    0.09
     школь
    0.09
    Activations Density 0.020%

    No Known Activations