© 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. 77977
    Prev
    Next
    INDEX
    Explanations

    wait

    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
     tabel
    -0.08
     encant
    -0.08
    commons
    -0.07
    ratings
    -0.07
     Curtis
    -0.07
     tavo
    -0.07
     progen
    -0.07
     bijvoorbeeld
    -0.07
     interpre
    -0.07
     aanzien
    -0.07
    POSITIVE LOGITS
     honestly
    0.09
    Oops
    0.09
     ADHD
    0.09
    ейчас
    0.09
    昨
    0.08
    ……”↵↵
    0.08
    っ
    0.08
    ajan
    0.07
     terlalu
    0.07
    …↵↵
    0.07
    Activations Density 0.030%

    No Known Activations