Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88005
    Prev
    Next
    INDEX
    Explanations

    appendix

    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
     Lords
    -0.08
    (&$
    -0.07
     هغې
    -0.07
    (↵
    -0.07
    (chars
    -0.07
    โลก
    -0.07
    ($.
    -0.07
    fox
    -0.07
    格
    -0.07
    endency
    -0.07
    POSITIVE LOGITS
     supplementary
    0.10
     supplemental
    0.09
     привед
    0.08
     Supplement
    0.08
     ergän
    0.08
     प्रस्तुत
    0.08
    ;q
    0.08
     matlab
    0.08
     tqdm
    0.08
    Supplement
    0.08
    Activations Density 0.002%

    No Known Activations