© 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. 24886
    Prev
    Next
    INDEX
    Explanations

    eyes

    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
     molecules
    -0.08
     nomen
    -0.08
     நிகழ
    -0.07
    mente
    -0.07
    _ps
    -0.07
     molecule
    -0.07
    Description
    -0.07
    ஆ
    -0.07
     world's
    -0.07
    (Note
    -0.07
    POSITIVE LOGITS
    睛
    0.11
    -eyed
    0.09
     keen
    0.09
     soar
    0.09
     atentos
    0.09
     kanan
    0.09
     exhilar
    0.08
     atento
    0.08
    joner
    0.08
     eyes
    0.08
    Activations Density 0.008%

    No Known Activations