© 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. 25958
    Prev
    Next
    INDEX
    Explanations

    documentation snippets

    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
     Advanced
    -0.07
     belang
    -0.07
     advertenties
    -0.07
     antig
    -0.07
    铭
    -0.07
     herd
    -0.07
    agency
    -0.07
     snapshots
    -0.07
     landlord
    -0.07
     ngos
    -0.07
    POSITIVE LOGITS
     તરીકે
    0.09
     lors
    0.09
     جهت
    0.09
     ενός
    0.08
     वाली
    0.08
     лечения
    0.08
     Ihres
    0.07
    Bei
    0.07
    の商品
    0.07
    付き
    0.07
    Activations Density 0.311%

    No Known Activations