© 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. 23-RESID-POST-AA
    11. 5880
    Prev
    Next
    INDEX
    Explanations

    É

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ицин
    -0.08
     V
    -0.08
     المورد
    -0.08
    Triangles
    -0.08
    िण
    -0.08
     région
    -0.08
    هج
    -0.08
     الجهات
    -0.07
     vliegtuig
    -0.07
     CGContext
    -0.07
    POSITIVE LOGITS
    pios
    0.08
    ARNING
    0.08
    _IMPORT
    0.08
     Hao
    0.08
    friendly
    0.08
    fio
    0.08
     Jing
    0.08
    Antonio
    0.07
    ampus
    0.07
     Aden
    0.07
    Activations Density 0.000%

    No Known Activations