© 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 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. 63467
    Prev
    Next
    INDEX
    Explanations

    Mixed code, Russian, items

    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
    .symmetric
    -0.10
     patios
    -0.09
     licensing
    -0.09
     clinics
    -0.08
     injunction
    -0.08
     Licensing
    -0.08
     Espan
    -0.08
     wetlands
    -0.08
     outsourcing
    -0.08
     STI
    -0.08
    POSITIVE LOGITS
     personalization
    0.09
     personnalisé
    0.09
     personalized
    0.09
     personalize
    0.08
     personalizada
    0.08
     Personalized
    0.08
    $link
    0.08
     personnalis
    0.08
     personalizados
    0.08
    队
    0.08
    Activations Density 0.003%

    No Known Activations