© 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. 30329
    Prev
    Next
    INDEX
    Explanations

    (

    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
    共同
    -0.11
     নিজেদের
    -0.10
     juntos
    -0.10
     gemeinsamen
    -0.09
     collectively
    -0.09
     gezamen
    -0.09
     gemeinsam
    -0.09
     jointly
    -0.09
    一起
    -0.09
     collaboratively
    -0.09
    POSITIVE LOGITS
     తన
    0.10
     തന്റെ
    0.09
     sozinho
    0.09
     solo
    0.08
     thesis
    0.08
     himself
    0.08
     herself
    0.07
    afx
    0.07
     pragma
    0.07
     jezelf
    0.07
    Activations Density 0.025%

    No Known Activations