© 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. 11-RESID-POST-AA
    11. 44354
    Prev
    Next
    INDEX
    Explanations

    digital age/information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alguno
    -0.07
     meerder
    -0.07
     trouver
    -0.07
    namen
    -0.07
     Нужно
    -0.07
    cery
    -0.07
    cu
    -0.07
     Courage
    -0.07
     Mean
    -0.07
     individuelle
    -0.07
    POSITIVE LOGITS
     globalization
    0.13
    全球
    0.13
     全球
    0.11
    科技
    0.11
     unprecedented
    0.11
    互联网
    0.11
     глоб
    0.11
     Digitalisierung
    0.11
     pandemia
    0.10
     neoliberal
    0.10
    Activations Density 0.041%

    No Known Activations