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. 43905
    Prev
    Next
    INDEX
    Explanations

    fuel

    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
     husband
    -0.08
    ixon
    -0.08
     ஸ
    -0.08
     நட
    -0.08
     ராஜ
    -0.07
     crane
    -0.07
     Ged
    -0.07
    -0.07
     deaf
    -0.07
     resign
    -0.07
    POSITIVE LOGITS
    aria
    0.09
    vite
    0.09
     angust
    0.08
     interstate
    0.08
     volatile
    0.08
    bond
    0.08
    buddy
    0.08
     Austral
    0.08
     potent
    0.08
    LAB
    0.08
    Activations Density 0.005%

    No Known Activations