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. 65290
    Prev
    Next
    INDEX
    Explanations

    Q

    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
    _stop
    -0.08
    (zip
    -0.08
     منها
    -0.08
    −
    -0.07
     inbound
    -0.07
     zipcode
    -0.07
    ビュー
    -0.07
     enforced
    -0.07
    zipcode
    -0.07
    .stop
    -0.07
    POSITIVE LOGITS
     Flutter
    0.12
    Flutter
    0.10
     Leo
    0.10
    _flutter
    0.09
     Ducati
    0.09
     Herbst
    0.09
     Coco
    0.09
     reinvent
    0.09
    Leo
    0.08
     Hermes
    0.08
    Activations Density 0.001%

    No Known Activations