© 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. 112511
    Prev
    Next
    INDEX
    Explanations

    y

    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
     трах
    -0.08
     Guillaume
    -0.08
    粤
    -0.08
    颗
    -0.08
    เด็ก
    -0.08
    场
    -0.07
    場
    -0.07
     authentic
    -0.07
     те
    -0.07
    充分
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.08
     letra
    0.08
     lettering
    0.07
    Proj
    0.07
    icone
    0.07
     snapped
    0.07
    esite
    0.07
    Oz
    0.07
    Projected
    0.07
     upto
    0.07
    Activations Density 0.037%

    No Known Activations