© 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. 25876
    Prev
    Next
    INDEX
    Explanations

    Lessons

    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
     negli
    -0.09
     Nws
    -0.08
     ubiquit
    -0.08
     Vand
    -0.08
     conspir
    -0.08
    দিন
    -0.07
    affle
    -0.07
    שרים
    -0.07
     busc
    -0.07
     gastr
    -0.07
    POSITIVE LOGITS
     Anfänger
    0.14
     beginners
    0.13
     beginner
    0.13
     нович
    0.12
    培训
    0.11
    初心
    0.11
     Beginner
    0.10
    教程
    0.10
     novice
    0.10
     newbies
    0.10
    Activations Density 0.050%

    No Known Activations