© 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. 19-RESID-POST-AA
    11. 103265
    Prev
    Next
    INDEX
    Explanations

    phrase

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sadece
    -0.09
     الوحيد
    -0.09
     standaard
    -0.08
     corrupted
    -0.08
    قطع
    -0.08
     parked
    -0.08
     تحتاج
    -0.08
    [])↵
    -0.08
     ainult
    -0.08
    مكن
    -0.08
    POSITIVE LOGITS
     it
    0.17
     elegantly
    0.16
     as
    0.16
     appropriately
    0.15
     nicely
    0.15
     in
    0.14
     זאת
    0.13
     красиво
    0.13
     accordingly
    0.13
     differently
    0.13
    Activations Density 0.014%

    No Known Activations