© 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. 110942
    Prev
    Next
    INDEX
    Explanations

    sleeve

    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
    �
    -0.09
    -0.08
    �
    -0.08
     ergonom
    -0.07
     Danny
    -0.07
     ame
    -0.07
     ergonomic
    -0.07
    	not
    -0.07
     dist
    -0.07
     cosine
    -0.07
    POSITIVE LOGITS
     thickness
    0.09
     Thickness
    0.08
    🏼
    0.08
     Sich
    0.08
     FULL
    0.08
    ful
    0.08
    厚
    0.08
    дум
    0.08
    RD
    0.07
     devotion
    0.07
    Activations Density 0.004%
    No Known Activations