© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 71170
    Prev
    Next
    INDEX
    Explanations

    minus

    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
     unm
    -0.08
     Bahamas
    -0.08
    (?)
    -0.07
     εμπ
    -0.07
     Kenntnisse
    -0.07
     Bark
    -0.07
     connaissances
    -0.07
     Kommunikation
    -0.07
     GIS
    -0.07
     Somalia
    -0.07
    POSITIVE LOGITS
     overloaded
    0.10
     preceding
    0.09
     preceded
    0.09
     '\
    0.09
    éf
    0.08
     Может
    0.08
     serpent
    0.08
    ('\
    0.08
     följ
    0.08
    :init
    0.08
    Activations Density 0.008%

    No Known Activations