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. 19226
    Prev
    Next
    INDEX
    Explanations

    Graph theory theorems

    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
    🙏
    -0.09
     esmal
    -0.08
     drills
    -0.08
     шест
    -0.08
    ebol
    -0.08
    _available
    -0.08
    Available
    -0.08
     meditation
    -0.08
    важ
    -0.08
    dee
    -0.08
    POSITIVE LOGITS
     bip
    0.11
     Bip
    0.10
     maximizing
    0.10
     avoiding
    0.09
     maxim
    0.09
     Maxim
    0.08
     optimizing
    0.08
     hedef
    0.08
    .recv
    0.08
    -density
    0.08
    Activations Density 0.008%

    No Known Activations