© 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. 11-RESID-POST-AA
    11. 863
    Prev
    Next
    INDEX
    Explanations

    Anemia

    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
     Aroma
    -0.08
    (top
    -0.08
    トップ
    -0.08
    .top
    -0.08
     Haunted
    -0.08
    .atan
    -0.08
    Ancestor
    -0.08
    ancestor
    -0.08
     kate
    -0.07
     اختیار
    -0.07
    POSITIVE LOGITS
     anemia
    0.13
    เลือ
    0.09
    oglobin
    0.09
     darah
    0.08
     bikin
    0.08
     sangre
    0.08
     supply
    0.08
     deficiencies
    0.08
     крови
    0.08
     literacy
    0.08
    Activations Density 0.007%

    No Known Activations