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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53099
    Prev
    Next
    INDEX
    Explanations

    Autoencoders

    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
     funks
    -0.08
     gemstone
    -0.08
     statutes
    -0.08
     peaches
    -0.08
     publicaciones
    -0.08
     claws
    -0.08
     Nick
    -0.08
     homicide
    -0.08
     noble
    -0.08
    zere
    -0.08
    POSITIVE LOGITS
     reconstruction
    0.08
     রিপ
    0.08
     ആവ
    0.08
     रिप
    0.08
     poorly
    0.08
     unmet
    0.08
     aufgenommen
    0.07
     satisfactory
    0.07
     goodness
    0.07
     обуч
    0.07
    Activations Density 0.002%

    No Known Activations