© 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. 99394
    Prev
    Next
    INDEX
    Explanations

    description

    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
    usu
    -0.09
     Communications
    -0.08
    Lith
    -0.08
    usz
    -0.08
    Authentication
    -0.08
     aure
    -0.08
    Zie
    -0.08
     Synchron
    -0.07
     Computes
    -0.07
    Did
    -0.07
    POSITIVE LOGITS
    都市
    0.08
     VP
    0.08
    garden
    0.07
    σα
    0.07
     τί
    0.07
     السوق
    0.07
     فتح
    0.07
     江
    0.07
     Corolla
    0.07
     河内
    0.07
    Activations Density 0.003%

    No Known Activations