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. 30561
    Prev
    Next
    INDEX
    Explanations

    nitrogen and chemical structures

    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
     उपाय
    -0.09
    .Compose
    -0.09
     bestselling
    -0.08
     marathon
    -0.08
     memahami
    -0.08
     Encycl
    -0.08
    ++↵↵
    -0.08
    &utm
    -0.08
     retail
    -0.08
    /Profile
    -0.08
    POSITIVE LOGITS
     peroxide
    0.11
     lone
    0.10
     phosphorus
    0.10
     nitr
    0.10
     nitrogen
    0.09
     aromatic
    0.09
     iodine
    0.09
     hydrogen
    0.09
     adjacent
    0.09
     bonded
    0.09
    Activations Density 0.008%

    No Known Activations