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. 109289
    Prev
    Next
    INDEX
    Explanations

    code and math symbols

    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
     delegation
    -0.08
     preparo
    -0.08
     erkl
    -0.07
     expansion
    -0.07
     Batch
    -0.07
     prep
    -0.07
     Preconditions
    -0.07
     pasti
    -0.07
    ərə
    -0.07
     expansão
    -0.07
    POSITIVE LOGITS
     sequential
    0.13
    Sequential
    0.12
     Sequential
    0.11
     consecut
    0.10
     לאורך
    0.10
    _sequence
    0.10
     consecutive
    0.09
     clockwise
    0.09
     sequ
    0.09
    Ordered
    0.09
    Activations Density 0.055%

    No Known Activations