© 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. 91826
    Prev
    Next
    INDEX
    Explanations

    Marketing blurbs

    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
     gelungen
    -0.09
     सुर
    -0.08
     डे
    -0.08
     volna
    -0.07
     guh
    -0.07
    进行了
    -0.07
     সংবাদ
    -0.07
     striking
    -0.07
     Rog
    -0.07
    vora
    -0.07
    POSITIVE LOGITS
     próxim
    0.14
     bientôt
    0.13
     soon
    0.13
     shortly
    0.12
     prochain
    0.11
     someday
    0.11
     It'll
    0.11
     sicuramente
    0.11
     estará
    0.10
     it'll
    0.10
    Activations Density 1.037%

    No Known Activations