© 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. 64076
    Prev
    Next
    INDEX
    Explanations

    =

    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
     kast
    -0.09
    ాల
    -0.08
    .pow
    -0.08
     episc
    -0.08
     Pelle
    -0.07
    ógicos
    -0.07
     Glide
    -0.07
    .om
    -0.07
     valley
    -0.07
    聯
    -0.07
    POSITIVE LOGITS
    fr
    0.08
     Yr
    0.08
     Sext
    0.07
    -we
    0.07
    /we
    0.07
     посвящ
    0.07
     MES
    0.07
     ///<
    0.07
     والذي
    0.07
     वो
    0.07
    Activations Density 0.004%

    No Known Activations