© 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. 70374
    Prev
    Next
    INDEX
    Explanations

    Transistors/circuits

    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
     concaten
    -0.08
     covariance
    -0.08
    continued
    -0.07
    conc
    -0.07
    .Iterator
    -0.07
    -0.07
    必
    -0.07
    364
    -0.07
    just
    -0.07
    Contin
    -0.07
    POSITIVE LOGITS
     servant
    0.09
    ρους
    0.09
     Desa
    0.09
     Kör
    0.08
    _launcher
    0.08
     Verde
    0.08
     kelas
    0.08
     Village
    0.08
    Village
    0.08
     Lah
    0.08
    Activations Density 0.002%
    No Known Activations