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. 43738
    Prev
    Next
    INDEX
    Explanations

    en

    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
     Ness
    -0.08
    当地
    -0.08
     realización
    -0.08
     чар
    -0.08
     nef
    -0.08
     superb
    -0.07
     lightning
    -0.07
     sid
    -0.07
     Runde
    -0.07
     existent
    -0.07
    POSITIVE LOGITS
    tbody
    0.08
     Bradford
    0.08
    uky
    0.07
     Purpose
    0.07
    brew
    0.07
     ISO
    0.07
    _<?
    0.07
     रव
    0.07
    ashay
    0.07
    Purpose
    0.07
    Activations Density 0.001%

    No Known Activations