© 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. 11-RESID-POST-AA
    11. 112639
    Prev
    Next
    INDEX
    Explanations

    delivery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    options
    -0.09
    orl
    -0.08
    itle
    -0.08
    ittle
    -0.08
    ité
    -0.07
    settings
    -0.07
     options
    -0.07
    	options
    -0.07
    dir
    -0.07
    ിറ്റി
    -0.07
    POSITIVE LOGITS
     receberam
    0.09
     دیده
    0.08
    REV
    0.08
    خته
    0.08
    вают
    0.08
     REV
    0.08
    (part
    0.08
    ยาย
    0.08
    eiende
    0.08
    ataifa
    0.08
    Activations Density 0.000%

    No Known Activations