© 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 EvalsExportsinterp-engineNEWAPI 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. 70142
    Prev
    Next
    INDEX
    Explanations

    after

    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
     reposition
    -0.09
     renewed
    -0.08
    baarheid
    -0.08
    ерш
    -0.08
    DG
    -0.08
    نع
    -0.08
    амат
    -0.08
    िंदगी
    -0.08
    弹
    -0.07
     NP
    -0.07
    POSITIVE LOGITS
    期間
    0.14
    期间
    0.12
     동안
    0.10
     jooksul
    0.10
     기간
    0.09
    期限
    0.09
    結果
    0.08
     probabil
    0.08
    भर
    0.08
     során
    0.08
    Activations Density 0.059%

    No Known Activations