© 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. 70832
    Prev
    Next
    INDEX
    Explanations

    Mythical creatures

    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
    畅
    -0.08
     mindfulness
    -0.08
    poon
    -0.08
    .elem
    -0.08
     chak
    -0.08
    uminium
    -0.08
    iding
    -0.08
    tors
    -0.08
     vacation
    -0.08
    imestre
    -0.08
    POSITIVE LOGITS
     Randolph
    0.08
    _ENTITY
    0.08
    Resolver
    0.08
    anska
    0.08
     ജീവ
    0.08
    Comma
    0.07
     kou
    0.07
    :http
    0.07
     Ком
    0.07
     blended
    0.07
    Activations Density 0.001%

    No Known Activations