© 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. 23-RESID-POST-AA
    11. 52094
    Prev
    Next
    INDEX
    Explanations

    灭

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     vloe
    -0.08
     rush
    -0.07
    ittura
    -0.07
    fér
    -0.07
     matured
    -0.07
     thrust
    -0.07
    .insert
    -0.07
     squeezing
    -0.07
    писок
    -0.07
    034
    -0.07
    POSITIVE LOGITS
    菌
    0.13
    绝
    0.10
    毒
    0.09
     Absolute
    0.09
    火
    0.09
    疫
    0.09
    �
    0.08
    absolute
    0.08
    傷
    0.08
    灭
    0.08
    Activations Density 0.003%

    No Known Activations