© 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. 114154
    Prev
    Next
    INDEX
    Explanations

    Parsing math word problems

    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
    ason
    -0.08
     UC
    -0.08
    ıda
    -0.08
     caliber
    -0.07
    ában
    -0.07
     jiro
    -0.07
     sexuelle
    -0.07
    .avatar
    -0.07
    carbonate
    -0.07
     capsule
    -0.07
    POSITIVE LOGITS
    (火
    0.10
    _vs
    0.08
    VS
    0.08
    Vs
    0.08
     drugi
    0.08
    पह
    0.08
     sends
    0.08
     väga
    0.08
     vf
    0.08
     malfunction
    0.08
    Activations Density 0.050%

    No Known Activations