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. 78516
    Prev
    Next
    INDEX
    Explanations

    the

    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
    _HISTORY
    -0.08
    history
    -0.08
     BALL
    -0.08
    -history
    -0.08
     快乐
    -0.08
    -ball
    -0.08
     thankful
    -0.08
    /history
    -0.07
     thieves
    -0.07
     HISTORY
    -0.07
    POSITIVE LOGITS
    Instrumentation
    0.10
     troops
    0.09
     instrumentation
    0.08
     materias
    0.08
    pecific
    0.08
     সেন
    0.08
     instruments
    0.07
     assembl
    0.07
     escal
    0.07
     significa
    0.07
    Activations Density 0.014%

    No Known Activations