© 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. 29120
    Prev
    Next
    INDEX
    Explanations

    Excel file processing

    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
     Longitude
    -0.09
     vert
    -0.08
     Elk
    -0.08
    าฟ
    -0.08
     multiline
    -0.08
     tern
    -0.08
    Longitude
    -0.08
    ністю
    -0.07
     Vert
    -0.07
     longitude
    -0.07
    POSITIVE LOGITS
     تعزيز
    0.09
     ضمان
    0.09
     تطبيق
    0.08
     marco
    0.08
     إطار
    0.08
     شام
    0.07
     אויב
    0.07
     Scholars
    0.07
    ppers
    0.07
    see
    0.07
    Activations Density 0.000%

    No Known Activations