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. 58579
    Prev
    Next
    INDEX
    Explanations

    Android XML layouts

    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
    DNA
    -0.09
     casin
    -0.08
    -life
    -0.08
     phạm
    -0.08
     DNA
    -0.08
     concierge
    -0.08
     undertaken
    -0.08
     зн
    -0.08
     Whois
    -0.08
     stale
    -0.08
    POSITIVE LOGITS
    layout
    0.10
     Multi
    0.09
    Hier
    0.09
     layout
    0.09
     Horizontal
    0.09
     Hier
    0.09
     Layout
    0.08
    hier
    0.08
     multip
    0.08
     Image
    0.08
    Activations Density 0.005%

    No Known Activations