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. 43964
    Prev
    Next
    INDEX
    Explanations

    Art patronage

    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
     rinse
    -0.10
     annoy
    -0.08
    (:,
    -0.08
    plain
    -0.08
     hourly
    -0.08
     rins
    -0.08
    _uploaded
    -0.08
    ipes
    -0.08
    腿
    -0.07
    legs
    -0.07
    POSITIVE LOGITS
     patron
    0.13
     patrons
    0.12
     lavish
    0.11
     Patron
    0.10
     sponsoring
    0.10
     commissioning
    0.10
     कलाकार
    0.09
     extravagant
    0.09
    赞
    0.09
     entertainment
    0.09
    Activations Density 0.022%

    No Known Activations