© 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. 111396
    Prev
    Next
    INDEX
    Explanations

    astrology

    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
     kamer
    -0.08
     aneur
    -0.08
    Slim
    -0.08
    Bulk
    -0.08
     bulk
    -0.07
     lar
    -0.07
     radio
    -0.07
    Pak
    -0.07
     nanop
    -0.07
     packaged
    -0.07
    POSITIVE LOGITS
     duke
    0.09
     �
    0.09
    hebb
    0.09
    认可
    0.09
     Allowed
    0.08
     recommandé
    0.08
     három
    0.08
     Constitucional
    0.08
     మూడు
    0.08
     Cardinal
    0.08
    Activations Density 0.005%

    No Known Activations