© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 25861
    Prev
    Next
    INDEX
    Explanations

    symmetric

    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
     yarn
    -0.08
     Microsoft
    -0.07
     resent
    -0.07
     eres
    -0.07
    нув
    -0.07
    _FE
    -0.07
     lod
    -0.07
     Türk
    -0.07
     oh
    -0.07
     kerül
    -0.07
    POSITIVE LOGITS
     nicely
    0.09
    性质
    0.08
    Curve
    0.08
     wickets
    0.08
     symmetrical
    0.08
    Cats
    0.08
    cats
    0.07
     sayesinde
    0.07
    Buckets
    0.07
    ispo
    0.07
    Activations Density 0.011%

    No Known Activations