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

    Neuronpedia

    APICircuit 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. 75943
    Prev
    Next
    INDEX
    Explanations

    Pipelining

    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
    icits
    -0.08
    <Game
    -0.08
     lear
    -0.08
    icit
    -0.07
     onclick
    -0.07
    <u
    -0.07
    591
    -0.07
    -game
    -0.07
    <Event
    -0.07
    <Application
    -0.07
    POSITIVE LOGITS
     stagger
    0.11
    _pipeline
    0.10
     sliding
    0.10
    pipeline
    0.09
     piling
    0.09
     Workflow
    0.09
    _BATCH
    0.09
     Pipeline
    0.09
     staggering
    0.09
     pipeline
    0.09
    Activations Density 0.026%

    No Known Activations