© 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. 18949
    Prev
    Next
    INDEX
    Explanations

    nuance

    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
     xwb
    -0.09
    ראת
    -0.09
     xov
    -0.08
    -lock
    -0.08
     الخارجية
    -0.08
    овательно
    -0.08
     ഏറ്റ
    -0.08
    外挂
    -0.08
    ственную
    -0.08
     externally
    -0.08
    POSITIVE LOGITS
     nuanced
    0.24
     nuance
    0.23
     nuances
    0.20
     гораздо
    0.15
     намного
    0.14
     ню
    0.14
     subt
    0.13
    もっと
    0.12
    Nu
    0.11
     mucho
    0.11
    Activations Density 0.021%

    No Known Activations