© 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. 68514
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     eign
    -0.08
    Ocean
    -0.08
    -provoking
    -0.08
     вообще
    -0.07
     指
    -0.07
     briefing
    -0.07
    (Property
    -0.07
    म्प
    -0.07
     oploss
    -0.07
    zion
    -0.07
    POSITIVE LOGITS
     Dennoch
    0.09
     having
    0.08
     Trotzdem
    0.08
     Є
    0.07
     Tiene
    0.07
    .RE
    0.07
     Cock
    0.07
     cnt
    0.07
    ਿਤ
    0.07
     Nuestra
    0.07
    Activations Density 0.043%

    No Known Activations