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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69902
    Prev
    Next
    INDEX
    Explanations

    neuron protection

    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
    Dropdown
    -0.10
     announcement
    -0.09
     وع
    -0.08
     announcing
    -0.08
    Doors
    -0.08
     Monopoly
    -0.08
    Markup
    -0.08
     DHCP
    -0.08
    Announcement
    -0.08
     Dropdown
    -0.08
    POSITIVE LOGITS
     oxidative
    0.18
     antioxid
    0.16
     antioxidant
    0.16
     antioxidants
    0.15
     injury
    0.15
     apoptosis
    0.14
     آسیب
    0.13
     inflammation
    0.13
     protecting
    0.13
    保护
    0.13
    Activations Density 0.018%

    No Known Activations