© 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. 3-RESID-POST-AA
    11. 12958
    Prev
    Next
    INDEX
    Explanations

    Leap years and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    desk
    -0.08
     SLA
    -0.08
     práce
    -0.08
    पर
    -0.07
     ethos
    -0.07
    发挥
    -0.07
    �
    -0.07
    喊
    -0.07
     antennas
    -0.07
     vibes
    -0.07
    POSITIVE LOGITS
    年份
    0.10
     chand
    0.09
     çift
    0.09
     сур
    0.09
     İ
    0.09
     বছ
    0.09
     century
    0.08
     தேர்த
    0.08
     শত
    0.08
     సంవత్సర
    0.08
    Activations Density 0.046%

    No Known Activations