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. 11821
    Prev
    Next
    INDEX
    Explanations

    ave

    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
     आधारित
    -0.09
     baud
    -0.08
     year
    -0.08
     cereal
    -0.08
     tangible
    -0.08
    -liter
    -0.08
     unbiased
    -0.08
    �
    -0.07
     Dryer
    -0.07
    -based
    -0.07
    POSITIVE LOGITS
     protr
    0.10
     folds
    0.09
     అక
    0.08
     pores
    0.08
    holes
    0.08
     accommodating
    0.08
     holes
    0.08
     ঢ
    0.08
     envers
    0.07
     sév
    0.07
    Activations Density 0.004%

    No Known Activations