© 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. 50975
    Prev
    Next
    INDEX
    Explanations

    England and Britain

    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
     pesos
    -0.10
     Haitian
    -0.10
     Gustavo
    -0.09
     repart
    -0.09
     Lula
    -0.09
    麻豆
    -0.09
     grinders
    -0.08
     Mexican
    -0.08
     Cuban
    -0.08
     Oaxaca
    -0.08
    POSITIVE LOGITS
    英国
    0.33
     England
    0.31
     UK
    0.29
     британ
    0.29
     Britse
    0.27
     britannique
    0.27
     British
    0.27
     ब्रिट
    0.27
    England
    0.27
     Britain
    0.26
    Activations Density 0.429%

    No Known Activations