© 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. 70973
    Prev
    Next
    INDEX
    Explanations

    away

    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
    _GPU
    -0.08
    스를
    -0.07
     globally
    -0.07
    _ETH
    -0.07
    rpc
    -0.07
     ACC
    -0.07
     globalization
    -0.07
    .js
    -0.07
    .testing
    -0.07
     DLC
    -0.07
    POSITIVE LOGITS
     belakang
    0.09
     доволь
    0.09
     disappointed
    0.09
     sluts
    0.09
     peanuts
    0.09
     Jumat
    0.08
     afternoons
    0.08
     naše
    0.08
    รู้
    0.08
    大道
    0.08
    Activations Density 0.020%

    No Known Activations