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. 88028
    Prev
    Next
    INDEX
    Explanations

    UI event handling

    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
     breakfast
    -0.08
     Arctic
    -0.08
     Frühstück
    -0.08
     motivational
    -0.08
     downloading
    -0.08
     Breakfast
    -0.08
    坊
    -0.08
    -selling
    -0.07
    -sama
    -0.07
    Downloading
    -0.07
    POSITIVE LOGITS
    Unhandled
    0.11
     이벤트
    0.10
     전달
    0.10
     события
    0.10
    dispatch
    0.10
     처리
    0.09
    keydown
    0.09
     delegated
    0.09
     dispatched
    0.09
     собы
    0.09
    Activations Density 0.004%

    No Known Activations