© 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. 109916
    Prev
    Next
    INDEX
    Explanations

    hanging

    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
     Oceans
    -0.08
    ><!--
    -0.08
    <!--
    -0.07
     rapidement
    -0.07
     азы
    -0.07
     enorm
    -0.07
     �
    -0.07
    Poll
    -0.07
    応
    -0.07
     thao
    -0.07
    POSITIVE LOGITS
    quarters
    0.09
     tube
    0.08
     quarter
    0.08
     Quarter
    0.08
     ratt
    0.08
     قائمة
    0.08
     shafts
    0.08
     precar
    0.08
     tubing
    0.07
     للح
    0.07
    Activations Density 0.008%

    No Known Activations