Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 428
    Prev
    Next
    INDEX
    Explanations

    Reading and dyslexia

    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
     Compass
    -0.08
    -demo
    -0.08
    極
    -0.08
    едж
    -0.08
     mgr
    -0.08
     desider
    -0.08
     공간
    -0.08
    .Lat
    -0.08
    .Azure
    -0.08
    conexion
    -0.08
    POSITIVE LOGITS
    阅读
    0.11
     decoding
    0.10
    読む
    0.10
     পড়
    0.10
     చద
    0.10
     વાંચ
    0.09
     পড়
    0.09
     decode
    0.09
     readability
    0.09
     mentally
    0.09
    Activations Density 0.012%

    No Known Activations