© 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. 71569
    Prev
    Next
    INDEX
    Explanations

    :

    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
     genießen
    -0.08
     Termin
    -0.08
     überrascht
    -0.07
     glowing
    -0.07
     如
    -0.07
     Gl
    -0.07
     vě
    -0.07
     enthusiast
    -0.07
     дем
    -0.07
     Starr
    -0.07
    POSITIVE LOGITS
     implica
    0.07
    엘
    0.07
     Jr
    0.07
    constexpr
    0.07
    bk
    0.07
     revolve
    0.07
    	dst
    0.07
     aigu
    0.07
     yab
    0.07
    Election
    0.07
    Activations Density 0.044%

    No Known Activations