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. 27393
    Prev
    Next
    INDEX
    Explanations

    scheduling delayed tasks

    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
     birt
    -0.08
     exhibited
    -0.08
     sey
    -0.07
    INI
    -0.07
     igen
    -0.07
     изделия
    -0.07
     feast
    -0.07
     exposed
    -0.07
     Exhibit
    -0.07
     breathe
    -0.07
    POSITIVE LOGITS
     delayed
    0.15
    Delayed
    0.14
    (delay
    0.12
     delay
    0.12
    .defer
    0.12
    .Delay
    0.12
     delaying
    0.12
    .delay
    0.12
     slated
    0.11
    _delay
    0.11
    Activations Density 0.007%

    No Known Activations