© 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. 44488
    Prev
    Next
    INDEX
    Explanations

    Parentheses

    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
    क्स
    -0.08
     Krishna
    -0.08
    flex
    -0.08
    迪
    -0.08
     Lucia
    -0.07
     devise
    -0.07
     barley
    -0.07
     mounting
    -0.07
     regla
    -0.07
     Klaus
    -0.07
    POSITIVE LOGITS
     smash
    0.09
     Shuffle
    0.08
    _shuffle
    0.08
    UM
    0.08
     naha
    0.07
     SAL
    0.07
     sanar
    0.07
    .echo
    0.07
     Siam
    0.07
    .ident
    0.07
    Activations Density 0.006%

    No Known Activations