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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54717
    Prev
    Next
    INDEX
    Explanations

    ERROR

    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
     laws
    -0.07
     padres
    -0.07
    법
    -0.07
     información
    -0.07
    unused
    -0.07
    积
    -0.07
    தில்
    -0.07
     Quebec
    -0.07
     कानून
    -0.07
     ಮಾಹಿತಿ
    -0.07
    POSITIVE LOGITS
    ís
    0.09
    Cleaner
    0.08
     Rasul
    0.08
    142
    0.08
    :end
    0.07
    เล่นสล็อต
    0.07
    ended
    0.07
    uler
    0.07
    fum
    0.07
     CPL
    0.07
    Activations Density 0.001%

    No Known Activations