© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44624
    Prev
    Next
    INDEX
    Explanations

    high

    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
     responsabilidades
    -0.08
                    ↵↵
    -0.08
            ↵↵
    -0.07
     Shade
    -0.07
     departments
    -0.07
    Department
    -0.07
     Starter
    -0.07
    selected
    -0.07
    department
    -0.07
                ↵↵
    -0.07
    POSITIVE LOGITS
    ুগ
    0.09
     похуд
    0.09
    走势
    0.09
     ઉત્પાદન
    0.08
     nový
    0.08
     üret
    0.08
     makam
    0.08
    (price
    0.08
     повышение
    0.08
     ઊ
    0.08
    Activations Density 0.001%

    No Known Activations