© 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. 692
    Prev
    Next
    INDEX
    Explanations

    code configuration

    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
    τό
    -0.08
    zero
    -0.08
     отдел
    -0.07
     ka
    -0.07
    motiv
    -0.07
    pane
    -0.07
     cadre
    -0.07
    termination
    -0.07
     ayrı
    -0.07
     stereotype
    -0.07
    POSITIVE LOGITS
     Reck
    0.09
     WHAT
    0.08
    推薦
    0.08
    快速
    0.08
    ാളെ
    0.08
     rapides
    0.07
     Andalucía
    0.07
     PASS
    0.07
     [&](
    0.07
     सुझ
    0.07
    Activations Density 0.146%

    No Known Activations