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. 12007
    Prev
    Next
    INDEX
    Explanations

    e

    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
     Tata
    -0.08
    wayne
    -0.08
     Zweifel
    -0.07
     Gesch
    -0.07
    .streaming
    -0.07
     voldoen
    -0.07
     Grammarly
    -0.07
     이제
    -0.07
     Sing
    -0.07
     dinosaurs
    -0.07
    POSITIVE LOGITS
    308
    0.08
    497
    0.08
    011
    0.08
     ops
    0.07
     induce
    0.07
    :",
    0.07
    ’ed
    0.07
    067
    0.07
    183
    0.07
    897
    0.07
    Activations Density 0.003%

    No Known Activations