© 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. 70239
    Prev
    Next
    INDEX
    Explanations

    Python code

    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
    ーパー
    -0.08
     swallowing
    -0.08
    ੱਡ
    -0.08
     evidente
    -0.08
    יד
    -0.08
     سند
    -0.08
     Electro
    -0.08
     teadm
    -0.08
    .gallery
    -0.08
     laminated
    -0.08
    POSITIVE LOGITS
     Mathemat
    0.10
     বাস্ত
    0.09
     MATLAB
    0.09
    \$
    0.09
     Umsetzung
    0.09
     computational
    0.09
     software
    0.09
     \$
    0.08
     গণ
    0.08
     informatique
    0.08
    Activations Density 0.059%

    No Known Activations