© 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. 64093
    Prev
    Next
    INDEX
    Explanations

    projective planes/graph theory

    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
     SER
    -0.09
     lip
    -0.09
    lip
    -0.08
     Lips
    -0.08
     Laurence
    -0.08
     kcal
    -0.08
     VAT
    -0.08
     baş
    -0.08
    Hourly
    -0.08
     SELL
    -0.08
    POSITIVE LOGITS
    ندر
    0.09
     congr
    0.08
     Ferm
    0.08
    	object
    0.08
    agde
    0.08
    Affine
    0.08
     coordin
    0.08
    conference
    0.08
     conference
    0.07
     victoire
    0.07
    Activations Density 0.005%

    No Known Activations