© 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. 19-RESID-POST-AA
    11. 102146
    Prev
    Next
    INDEX
    Explanations

    cultural

    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
    辉
    -0.09
     lavish
    -0.09
     spectaculaire
    -0.09
     elegantly
    -0.08
     stolz
    -0.08
     majestic
    -0.08
     magnificent
    -0.08
     breathtaking
    -0.08
     élégant
    -0.08
     proud
    -0.08
    POSITIVE LOGITS
     cultural
    0.20
     culturele
    0.16
     Cultural
    0.16
    文化
    0.16
     культур
    0.16
     cultura
    0.16
     kült
    0.16
     budaya
    0.15
     meme
    0.15
     culturais
    0.15
    Activations Density 0.016%

    No Known Activations