© 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. 75825
    Prev
    Next
    INDEX
    Explanations

    that

    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
     infatti
    -0.08
    psych
    -0.07
    ie
    -0.07
     ఎంద
    -0.07
    込
    -0.07
     powerhouse
    -0.07
     aka
    -0.07
    spann
    -0.07
     unrival
    -0.07
    abetes
    -0.07
    POSITIVE LOGITS
     تخص
    0.09
     overall
    0.09
     ضمن
    0.08
    ંટ
    0.08
     nonetheless
    0.08
     néanmoins
    0.08
     الجميع
    0.08
     કુલ
    0.08
    即可
    0.08
    Overall
    0.08
    Activations Density 0.041%

    No Known Activations