© 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. 19-RESID-POST-AA
    11. 103338
    Prev
    Next
    INDEX
    Explanations

    reviewing tasks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعرفة
    -0.09
     zama
    -0.09
     myös
    -0.09
     repeatedly
    -0.08
     use
    -0.08
     غني
    -0.08
    ucalyptus
    -0.08
     më
    -0.08
    erti
    -0.08
     גוף
    -0.08
    POSITIVE LOGITS
     yesterday
    0.18
    昨天
    0.18
    昨日
    0.17
    昨
    0.15
     Upcoming
    0.15
     pending
    0.15
    今晚
    0.15
    Upcoming
    0.15
    Yesterday
    0.15
     overnight
    0.14
    Activations Density 0.016%

    No Known Activations