© 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. 31608
    Prev
    Next
    INDEX
    Explanations

    2

    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
     친
    -0.08
    iriya
    -0.07
     yat
    -0.07
     vilja
    -0.07
     mong
    -0.07
     mutu
    -0.07
     수
    -0.07
     FETCH
    -0.07
    amilton
    -0.07
     obi
    -0.07
    POSITIVE LOGITS
     imag
    0.08
     inches
    0.08
     incidencia
    0.08
     Ingen
    0.08
     incidence
    0.08
     incid
    0.08
     angegeben
    0.08
     liters
    0.07
    平方米
    0.07
     indrukwekk
    0.07
    Activations Density 0.016%

    No Known Activations