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. 106320
    Prev
    Next
    INDEX
    Explanations

    extends, bound

    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
     dare
    -0.08
     samb
    -0.08
     ALG
    -0.08
     sam
    -0.08
     freaking
    -0.08
    stil
    -0.08
    _Play
    -0.08
    inali
    -0.08
    atriz
    -0.07
    拉特
    -0.07
    POSITIVE LOGITS
     "*.
    0.08
    ида
    0.07
     boeken
    0.07
     capt
    0.07
     constantemente
    0.07
     bounty
    0.07
     moe
    0.07
     '*.
    0.07
     humane
    0.07
     capitalism
    0.07
    Activations Density 0.001%

    No Known Activations