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

    Neuronpedia

    APICircuit 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. 11937
    Prev
    Next
    INDEX
    Explanations

    dream interpretation

    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
     callable
    -0.08
     план
    -0.07
    64
    -0.07
    At
    -0.07
     забезпеч
    -0.07
    32
    -0.07
     boosters
    -0.07
     booster
    -0.07
     прым
    -0.07
     artificially
    -0.07
    POSITIVE LOGITS
     Interpretation
    0.15
     interpretation
    0.14
     symbolism
    0.14
     interpretación
    0.14
     interpreting
    0.14
     interpretations
    0.14
     interpretação
    0.13
     تفسير
    0.13
     المنام
    0.13
    Interpret
    0.13
    Activations Density 0.058%

    No Known Activations