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. 43860
    Prev
    Next
    INDEX
    Explanations

    CPR

    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
    mont
    -0.08
     liking
    -0.08
     carv
    -0.08
     shelving
    -0.08
     czas
    -0.07
     lotto
    -0.07
    ू
    -0.07
     này
    -0.07
     Investig
    -0.07
     matérias
    -0.07
    POSITIVE LOGITS
    TRIES
    0.08
     tirelessly
    0.08
     Rotary
    0.08
    .Work
    0.08
    _Work
    0.08
    献
    0.08
    工作
    0.08
     relentlessly
    0.08
    _WORK
    0.08
    Trying
    0.08
    Activations Density 0.003%

    No Known Activations