© 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. 26371
    Prev
    Next
    INDEX
    Explanations

    medical tests and diagnoses

    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
    _Injected
    -0.08
     intérieure
    -0.08
     largura
    -0.08
     latt
    -0.08
     بلاد
    -0.07
    (width
    -0.07
     living
    -0.07
    orsz
    -0.07
     بن
    -0.07
    _inner
    -0.07
    POSITIVE LOGITS
     biomarkers
    0.12
     biom
    0.09
    -marker
    0.09
     Biom
    0.09
    Markers
    0.09
     quantify
    0.09
    .marker
    0.09
     Marker
    0.08
     Monitor
    0.08
     markers
    0.08
    Activations Density 0.005%

    No Known Activations