© 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. 114085
    Prev
    Next
    INDEX
    Explanations

    mathematical optimization

    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
     Firmware
    -0.09
    _src
    -0.09
    Entertainment
    -0.08
    (Duration
    -0.08
    Src
    -0.08
     Lorenzo
    -0.08
     dividends
    -0.08
     Unterstüt
    -0.08
    .Value
    -0.08
     dams
    -0.08
    POSITIVE LOGITS
     coordinates
    0.10
     boundary
    0.10
     reachable
    0.10
     simplex
    0.09
     Coordinates
    0.09
    Coordinates
    0.09
     manifold
    0.09
    boundary
    0.09
     Hess
    0.09
     stationary
    0.09
    Activations Density 0.019%

    No Known Activations