© 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. 11-RESID-POST-AA
    11. 114314
    Prev
    Next
    INDEX
    Explanations

    _header

    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
     representatives
    -0.08
     representative
    -0.08
     adaptés
    -0.08
     entrants
    -0.08
    <context
    -0.08
     urgent
    -0.08
    adata
    -0.08
    	driver
    -0.08
    (driver
    -0.07
    &period
    -0.07
    POSITIVE LOGITS
     Jail
    0.09
     Cham
    0.08
     gimnasio
    0.08
     jail
    0.08
    DECLARE
    0.08
     languages
    0.07
     exp
    0.07
    Cham
    0.07
     caffe
    0.07
     Tent
    0.07
    Activations Density 0.000%

    No Known Activations