© 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. 23-RESID-POST-AA
    11. 51529
    Prev
    Next
    INDEX
    Explanations

    Code or config snippets

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    自治
    -0.10
     autonomía
    -0.09
     autonomy
    -0.09
     Aut
    -0.08
     autonomia
    -0.08
     автоном
    -0.08
     autoc
    -0.08
     autón
    -0.08
     autonome
    -0.08
    リエ
    -0.07
    POSITIVE LOGITS
    زمة
    0.08
     espect
    0.08
    obiles
    0.07
     namm
    0.07
    ('/')
    0.07
     أنّ
    0.07
     infos
    0.07
    ‌اند
    0.07
    עוד
    0.07
    ’appar
    0.07
    Activations Density 0.001%

    No Known Activations