© 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. 95524
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities

    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
     Nobel
    -0.07
     أمري
    -0.07
    (un
    -0.07
    Translations
    -0.07
    -fledged
    -0.07
    kező
    -0.07
     generic
    -0.07
    ವಾದ
    -0.07
     Canton
    -0.07
     плеч
    -0.06
    POSITIVE LOGITS
    ','=','
    0.08
    ==-
    0.08
     ode
    0.08
     ",
↵
    0.08
     exce
    0.08
     להש
    0.08
    clk
    0.07
    ariya
    0.07
     stellt
    0.07
     gede
    0.07
    Activations Density 0.071%

    No Known Activations