© 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. 659
    Prev
    Next
    INDEX
    Explanations

    negative situations, system failures

    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
     Главное
    -0.08
     classy
    -0.08
     :)
    -0.08
     accidentally
    -0.08
     :)↵
    -0.08
     GUID
    -0.08
     Clap
    -0.08
     diy
    -0.08
     :)↵↵
    -0.08
     drawable
    -0.08
    POSITIVE LOGITS
     inadequate
    0.14
     plagued
    0.13
     agrav
    0.13
     inadequ
    0.12
     exacerb
    0.12
     હાલ
    0.12
     insufficient
    0.11
     struggles
    0.11
     desperately
    0.11
     grievances
    0.11
    Activations Density 0.192%

    No Known Activations