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. 15-RESID-POST-AA
    6. 19227
    Prev
    Next
    INDEX
    Explanations

    statistical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wreck
    -0.11
     Kali
    -0.10
     bitcoin
    -0.10
    bitcoin
    -0.10
     asteroid
    -0.09
     Salem
    -0.09
     deton
    -0.09
     dumpster
    -0.09
    Rune
    -0.09
    mouth
    -0.09
    POSITIVE LOGITS
     Nested
    0.10
     hierarchical
    0.10
     categorical
    0.10
     nested
    0.09
    -effects
    0.09
    Nested
    0.09
     nuisance
    0.09
     effets
    0.09
     moderators
    0.09
    Hier
    0.08
    Activations Density 0.006%

    No Known Activations