© 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. 114117
    Prev
    Next
    INDEX
    Explanations

    dive into a topic

    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
     Several
    -0.08
     Engineer
    -0.08
     Practical
    -0.08
     sogen
    -0.08
    atore
    -0.08
     استاند
    -0.08
     Pioneer
    -0.08
     Intermediate
    -0.08
    regeling
    -0.08
     valeurs
    -0.08
    POSITIVE LOGITS
     gerne
    0.08
     Ged
    0.08
     alsnog
    0.08
     autrement
    0.08
    ું
    0.08
     ee
    0.08
     noch
    0.08
    /show
    0.07
     gladly
    0.07
    もう
    0.07
    Activations Density 0.008%

    No Known Activations