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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12198
    Prev
    Next
    INDEX
    Explanations

    of

    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
    URIComponent
    -0.08
    .encode
    -0.08
    Prod
    -0.08
    BB
    -0.08
    herits
    -0.07
     unusually
    -0.07
     '${
    -0.07
     compiled
    -0.07
     वित्त
    -0.07
     BBC
    -0.07
    POSITIVE LOGITS
     veilige
    0.08
     utile
    0.08
     scheduling
    0.08
     anabolic
    0.08
     Scheduling
    0.08
     bezpe
    0.08
     útil
    0.08
    าป
    0.08
     tino
    0.07
    歌词
    0.07
    Activations Density 0.005%

    No Known Activations