© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103479
    Prev
    Next
    INDEX
    Explanations

    high

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teamed
    -0.09
     новое
    -0.09
    innov
    -0.09
     smiled
    -0.09
    happy
    -0.09
     empowered
    -0.09
    abled
    -0.09
    death
    -0.08
    answered
    -0.08
     fantastische
    -0.08
    POSITIVE LOGITS
     detail
    0.16
     accuracy
    0.16
     fidelity
    0.13
     clarity
    0.13
     precision
    0.13
     depth
    0.12
     detalle
    0.12
     regard
    0.12
     rigor
    0.12
     mathematical
    0.12
    Activations Density 0.003%

    No Known Activations