© 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. 31468
    Prev
    Next
    INDEX
    Explanations

    search engine optimization

    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
    Selected
    -0.09
     лекар
    -0.09
    嘛
    -0.09
     właści
    -0.08
     begleiten
    -0.08
     уют
    -0.08
     dispos
    -0.08
    .dispose
    -0.08
    edin
    -0.08
     निध
    -0.08
    POSITIVE LOGITS
     phishing
    0.11
    排名
    0.11
     SEO
    0.10
     crawler
    0.10
     spam
    0.10
     HTTPS
    0.10
     blacklist
    0.09
     whitelist
    0.09
     Gmail
    0.09
     Chrome
    0.09
    Activations Density 0.048%

    No Known Activations