© 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. 69691
    Prev
    Next
    INDEX
    Explanations

    remote

    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
    所在
    -0.10
     meten
    -0.07
     이름
    -0.07
     London's
    -0.07
    שם
    -0.07
     respond
    -0.07
     gush
    -0.07
    endl
    -0.07
     mut
    -0.07
    cen
    -0.07
    POSITIVE LOGITS
    ppt
    0.08
    stellar
    0.08
     onboarding
    0.08
     initiatives
    0.08
     nightmares
    0.08
    Tips
    0.08
     domic
    0.08
    ayas
    0.07
     entreprises
    0.07
     maupun
    0.07
    Activations Density 0.015%

    No Known Activations