© 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. 91617
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Herausforderungen
    -0.08
     nogle
    -0.08
    іра
    -0.08
    IPAddress
    -0.08
     hablado
    -0.08
     Daly
    -0.08
     habló
    -0.08
    /Image
    -0.07
     зд
    -0.07
    IPv
    -0.07
    POSITIVE LOGITS
     interested
    0.12
     누구
    0.10
     वरिष्ठ
    0.09
     كبار
    0.09
    .admin
    0.09
     senior
    0.09
    人员
    0.09
     interessados
    0.09
     policymakers
    0.08
     interesados
    0.08
    Activations Density 0.038%

    No Known Activations