© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75452
    Prev
    Next
    INDEX
    Explanations

    �

    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
     arbitration
    -0.09
     Esc
    -0.08
     Rig
    -0.08
     Arche
    -0.08
     Ports
    -0.08
    _port
    -0.08
     Strat
    -0.08
    -port
    -0.08
    型号
    -0.08
    _PORT
    -0.08
    POSITIVE LOGITS
     spars
    0.13
     sparse
    0.12
    Sparse
    0.09
    _sparse
    0.09
     Sparse
    0.09
    enet
    0.09
    busters
    0.08
    NESS
    0.08
     PME
    0.08
    Coupon
    0.08
    Activations Density 0.003%

    No Known Activations