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. 12953
    Prev
    Next
    INDEX
    Explanations

    code

    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
    acios
    -0.08
    先进
    -0.08
     koi
    -0.08
     anxious
    -0.08
    彻
    -0.07
     nerves
    -0.07
     exc
    -0.07
     izgled
    -0.07
    asuna
    -0.07
    chia
    -0.07
    POSITIVE LOGITS
    Ontology
    0.15
     ontology
    0.13
    .rdf
    0.11
     ont
    0.11
     rdf
    0.11
     Person
    0.11
     Semantic
    0.11
    ontology
    0.11
     facts
    0.11
     inferred
    0.10
    Activations Density 0.021%

    No Known Activations