© 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. 23-RESID-POST-AA
    11. 49710
    Prev
    Next
    INDEX
    Explanations

    say "where center follows"

    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
     chaînes
    -0.10
    Paperback
    -0.10
     chaîne
    -0.09
    موية
    -0.09
    افی
    -0.09
    Publié
    -0.09
     película
    -0.09
    ివ్
    -0.08
    mür
    -0.08
    ڊي
    -0.08
    POSITIVE LOGITS
    center
    0.18
    .center
    0.14
     center
    0.14
    venter
    0.14
    _center
    0.14
    -center
    0.14
     центр
    0.13
    centrum
    0.13
    .CENTER
    0.12
    	center
    0.12
    Activations Density 0.005%

    No Known Activations