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. 30629
    Prev
    Next
    INDEX
    Explanations

    Names and locations

    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
     tinha
    -0.08
    aternity
    -0.08
     oxide
    -0.07
    trib
    -0.07
     didn
    -0.07
    _GP
    -0.07
     theatr
    -0.07
     Karin
    -0.07
     phy
    -0.07
     rubber
    -0.07
    POSITIVE LOGITS
    .Index
    0.09
     происходит
    0.08
     ONE
    0.08
     Speicher
    0.08
    INDEX
    0.08
     stesso
    0.08
     INDEX
    0.07
     Yun
    0.07
     видно
    0.07
    _OCCURRED
    0.07
    Activations Density 0.197%

    No Known Activations