© 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. 25208
    Prev
    Next
    INDEX
    Explanations

    part

    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
     adipiscing
    -0.08
    world
    -0.08
     ಆಚ
    -0.08
    compressed
    -0.07
     производства
    -0.07
     frame
    -0.07
     Occ
    -0.07
    kra
    -0.07
     prescription
    -0.07
     тысячи
    -0.07
    POSITIVE LOGITS
     iii
    0.09
    iii
    0.09
    ：(
    0.09
    ：（
    0.08
    /problem
    0.08
    Ell
    0.08
    (ii
    0.08
    _toggle
    0.08
    quisite
    0.08
    भाग
    0.08
    Activations Density 0.020%

    No Known Activations