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. 104299
    Prev
    Next
    INDEX
    Explanations

    File paths

    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
    Holiday
    -0.08
     side
    -0.08
    .side
    -0.08
     harness
    -0.08
    Spawn
    -0.07
     energ
    -0.07
    -0.07
    .spawn
    -0.07
     stopwatch
    -0.07
    SIDE
    -0.07
    POSITIVE LOGITS
     hierarchy
    0.15
     hierarchical
    0.14
     Hier
    0.14
    Hier
    0.13
    Hierarchy
    0.13
     nesting
    0.13
    三级
    0.12
     hier
    0.12
    hier
    0.12
    _nested
    0.12
    Activations Density 0.012%

    No Known Activations