© 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. 26091
    Prev
    Next
    INDEX
    Explanations

    you

    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
    Common
    -0.08
    (common
    -0.08
    /common
    -0.08
    common
    -0.08
    ykl
    -0.07
    (Common
    -0.07
     тенден
    -0.07
    sun
    -0.07
    をご
    -0.07
    vous
    -0.07
    POSITIVE LOGITS
    Needed
    0.10
     needed
    0.10
     necessidades
    0.09
     Needed
    0.09
     chọrọ
    0.09
    needed
    0.09
    _needed
    0.08
     يحتاج
    0.08
     തന്നെ
    0.08
    حتاج
    0.08
    Activations Density 0.019%

    No Known Activations