© 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. 91582
    Prev
    Next
    INDEX
    Explanations

    Zettelkasten method

    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
     variations
    -0.08
     varieties
    -0.08
    961
    -0.08
     unacceptable
    -0.08
    �
    -0.08
     ripe
    -0.08
     ಧ
    -0.07
    resión
    -0.07
     Sesame
    -0.07
     thương
    -0.07
    POSITIVE LOGITS
     സംവിധാനം
    0.09
     лок
    0.08
     libero
    0.08
     Income
    0.08
     Nagar
    0.07
     Guidance
    0.07
    கர
    0.07
     yönt
    0.07
     লোক
    0.07
     कोरो
    0.07
    Activations Density 0.001%

    No Known Activations