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. 29925
    Prev
    Next
    INDEX
    Explanations

    where to watch content

    np_max-act · gemini-2.0-flash

    This attention head attends to the start of the text from various points later in the text.

    oai_attention-head · gpt-4oTriggered by @mlfinancebook
    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
     GPIO
    -0.09
     Yang
    -0.08
     XA
    -0.08
    Ye
    -0.08
    Yang
    -0.08
     Interaction
    -0.08
    锋
    -0.08
     aggress
    -0.08
    alala
    -0.08
    Interaction
    -0.08
    POSITIVE LOGITS
    免费在线观看
    0.11
    免费观看
    0.11
    免费播放
    0.10
     licensed
    0.10
     authorized
    0.09
    观看
    0.09
     rental
    0.09
     находится
    0.08
     лиценз
    0.08
     authorised
    0.08
    Activations Density 0.036%

    No Known Activations