© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 109950
    Prev
    Next
    INDEX
    Explanations

    Arduino pins and interrupts

    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
    Negative Logits
     fór
    -0.08
     sanctioned
    -0.08
     propriet
    -0.08
     Propriet
    -0.07
     transplantation
    -0.07
     cmd
    -0.07
    vira
    -0.07
    env
    -0.07
     licencia
    -0.07
     lic
    -0.07
    POSITIVE LOGITS
    ماع
    0.11
     interrupts
    0.10
    报警
    0.10
     alarms
    0.10
    _alarm
    0.10
    监听
    0.10
     noises
    0.10
     noisy
    0.10
     seizures
    0.10
     bekommst
    0.09
    Activations Density 0.004%

    No Known Activations