© 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 EvalsExportsinterp-engineNEWAPI 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. 110657
    Prev
    Next
    INDEX
    Explanations

    matcha

    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
    _void
    -0.08
     Chains
    -0.08
     chains
    -0.07
     void
    -0.07
     permissions
    -0.07
     Podcasts
    -0.07
     hostage
    -0.07
    .Network
    -0.07
     Cecil
    -0.07
     Cy
    -0.07
    POSITIVE LOGITS
     latte
    0.10
    ulag
    0.09
     uki
    0.08
     Latte
    0.08
    Adobe
    0.08
     culturel
    0.08
     danza
    0.08
    Tat
    0.08
    تق
    0.08
    Cafe
    0.08
    Activations Density 0.004%

    No Known Activations