© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129526
    Prev
    Next
    INDEX
    Explanations

    став

    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
     ساخت
    -0.08
    eee
    -0.08
     Dun
    -0.08
     Emin
    -0.07
     Ghana
    -0.07
     Aurora
    -0.07
     Nj
    -0.07
    verg
    -0.07
     overt
    -0.07
     THC
    -0.07
    POSITIVE LOGITS
    -Bar
    0.07
    Importer
    0.07
     dioxide
    0.07
     Cove
    0.07
     реш
    0.07
     devised
    0.07
    िक
    0.07
    _logits
    0.07
     deport
    0.07
     quo
    0.07
    Activations Density 0.024%

    No Known Activations