Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 112012
    Prev
    Next
    INDEX
    Explanations

    work

    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
    .strip
    -0.08
    .circle
    -0.08
    (flag
    -0.08
    rack
    -0.08
    _sv
    -0.08
    /root
    -0.07
    -R
    -0.07
    igation
    -0.07
    igon
    -0.07
     retirar
    -0.07
    POSITIVE LOGITS
     professionals
    0.10
     업무
    0.09
     ums
    0.08
     seasoned
    0.08
     Professionals
    0.08
     المهنية
    0.08
    tsa
    0.08
    жә
    0.08
     praktische
    0.08
     beroeps
    0.08
    Activations Density 0.020%

    No Known Activations