© 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. 95074
    Prev
    Next
    INDEX
    Explanations

    programming variables

    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
    loid
    -0.08
     Toutefois
    -0.08
    usetzen
    -0.08
     genders
    -0.07
     pleasing
    -0.07
     flooded
    -0.07
    Payments
    -0.07
     ವಾಹ
    -0.07
     모집
    -0.07
     tritur
    -0.07
    POSITIVE LOGITS
     Intelli
    0.08
    ै
    0.07
    lady
    0.07
     wali
    0.07
     Shin
    0.07
     inadvertently
    0.07
    bus
    0.07
     ****
    0.07
     ******
    0.07
     foo
    0.07
    Activations Density 0.011%

    No Known Activations