© 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 EvalsExportsAPI 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. 63645
    Prev
    Next
    INDEX
    Explanations

    Music titles

    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
     literacy
    -0.09
     δι
    -0.08
    _reporting
    -0.08
    责
    -0.08
     nutrition
    -0.08
    .Validator
    -0.08
    Vacc
    -0.08
     vaccination
    -0.08
     workforce
    -0.08
    .Batch
    -0.08
    POSITIVE LOGITS
     Prelude
    0.09
     Meditation
    0.09
     Trio
    0.08
     improvis
    0.08
     मुफ
    0.08
     Ambient
    0.08
     Orch
    0.08
    artige
    0.08
     meditation
    0.08
     Sonata
    0.07
    Activations Density 0.022%

    No Known Activations