© 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. 78955
    Prev
    Next
    INDEX
    Explanations

    Ant

    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
    ימוש
    -0.08
    Å
    -0.08
    一起
    -0.08
     Heb
    -0.08
     uży
    -0.08
     gehele
    -0.07
    NSUser
    -0.07
    તી
    -0.07
     Reich
    -0.07
    เอ
    -0.07
    POSITIVE LOGITS
     profesora
    0.08
     gir
    0.07
     professora
    0.07
     gase
    0.07
     grem
    0.07
    _WHITE
    0.07
     cercana
    0.07
     ministra
    0.07
    マー
    0.07
     vicepres
    0.07
    Activations Density 0.000%

    No Known Activations