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. 88301
    Prev
    Next
    INDEX
    Explanations

    futures

    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
     sinc
    -0.09
     HPV
    -0.08
     guér
    -0.08
     itiner
    -0.08
     inspir
    -0.07
    Ara
    -0.07
    mero
    -0.07
    大家
    -0.07
    流程
    -0.07
    デル
    -0.07
    POSITIVE LOGITS
     journalism
    0.08
     Revision
    0.08
    (Command
    0.07
    _pkg
    0.07
    (Print
    0.07
     אחר
    0.07
     Master's
    0.07
    _Command
    0.07
     obedience
    0.07
     Pod
    0.07
    Activations Density 0.001%

    No Known Activations