© 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. 23-RESID-POST-AA
    11. 6455
    Prev
    Next
    INDEX
    Explanations

    CSS "wrap" property

    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
    артам
    -0.08
     yellow
    -0.08
    antic
    -0.08
     unfolding
    -0.07
     agrad
    -0.07
    oxy
    -0.07
     Yellow
    -0.07
    ollipop
    -0.07
     مرتب
    -0.07
    ers
    -0.07
    POSITIVE LOGITS
    -wrap
    0.10
    .wrap
    0.08
    Wrap
    0.08
    .CR
    0.08
     dieren
    0.08
    _wrap
    0.07
    Ani
    0.07
     lang
    0.07
    Anim
    0.07
    _AN
    0.07
    Activations Density 0.015%

    No Known Activations