© 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. 19-RESID-POST-AA
    11. 18822
    Prev
    Next
    INDEX
    Explanations

    verbose

    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
    recognized
    -0.10
     tangible
    -0.09
     nyata
    -0.08
     dependable
    -0.08
     effektiv
    -0.08
    -aware
    -0.08
     बेहतर
    -0.08
     reliable
    -0.08
    675
    -0.08
     موثر
    -0.08
    POSITIVE LOGITS
     lengthy
    0.24
     подроб
    0.19
     длин
    0.18
     verbose
    0.18
     verbosity
    0.18
    詳細
    0.17
     jargon
    0.17
     déta
    0.17
     detaljer
    0.17
     détails
    0.17
    Activations Density 0.038%

    No Known Activations