© 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. 109802
    Prev
    Next
    INDEX
    Explanations

    stone

    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
    nahme
    -0.08
     belasting
    -0.08
    nahmen
    -0.08
     Casey
    -0.08
     став
    -0.08
    stv
    -0.08
     stagger
    -0.08
     hectares
    -0.08
    ihugu
    -0.08
    ountries
    -0.08
    POSITIVE LOGITS
    文明
    0.10
     circuitry
    0.09
     mining
    0.09
     milling
    0.08
    Mes
    0.08
     asociados
    0.07
    不停
    0.07
     Mes
    0.07
     machining
    0.07
     eche
    0.07
    Activations Density 0.001%

    No Known Activations