© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 97678
    Prev
    Next
    INDEX
    Explanations

    Middle Eastern countries

    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
     Māori
    -0.12
     Hindu
    -0.10
     京都
    -0.10
     храм
    -0.10
     Buddhist
    -0.09
     Vais
    -0.09
     Gaelic
    -0.09
    黄大仙
    -0.09
     Whak
    -0.09
     chakra
    -0.09
    POSITIVE LOGITS
     Tunisia
    0.16
     Egypt
    0.16
     Algeria
    0.15
     Libya
    0.15
     Jordan
    0.15
    Jordan
    0.15
     تونس
    0.14
     Egyptian
    0.14
     Lib
    0.14
     Alger
    0.14
    Activations Density 0.018%

    No Known Activations