© 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. 64024
    Prev
    Next
    INDEX
    Explanations

    sum of

    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
     төл
    -0.08
     replacing
    -0.08
    okka
    -0.08
    orith
    -0.08
     consectetur
    -0.08
    Ross
    -0.07
    .Fprintf
    -0.07
     faiz
    -0.07
     rääk
    -0.07
    傅
    -0.07
    POSITIVE LOGITS
     서로
    0.09
     ampliamente
    0.09
    双方
    0.09
     miteinander
    0.08
     pov
    0.08
     bonding
    0.08
     mingle
    0.08
    .compose
    0.08
     المشتر
    0.08
     gemeinsamen
    0.08
    Activations Density 0.016%

    No Known Activations