© 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. 19098
    Prev
    Next
    INDEX
    Explanations

    Europe

    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
     disper
    -0.08
     plaintext
    -0.07
     transcription
    -0.07
     electricidad
    -0.07
     нам
    -0.07
     electrical
    -0.07
     tiếp
    -0.07
     électriques
    -0.07
    Electrical
    -0.07
    irst
    -0.07
    POSITIVE LOGITS
    欧洲
    0.20
     欧洲
    0.19
     Europe
    0.19
     European
    0.19
     europeos
    0.18
     Европе
    0.18
     europäischen
    0.18
     europeu
    0.17
    European
    0.17
     европей
    0.17
    Activations Density 0.046%

    No Known Activations