© 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. 110116
    Prev
    Next
    INDEX
    Explanations

    smoke

    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
    agnes
    -0.09
    ían
    -0.08
     Xer
    -0.08
     PHPUnit
    -0.08
     ponen
    -0.07
     ques
    -0.07
     Vogel
    -0.07
    ardige
    -0.07
    _Page
    -0.07
     unrestricted
    -0.07
    POSITIVE LOGITS
     सैनिक
    0.10
     morg
    0.09
     каз
    0.08
     soldiers
    0.08
     трав
    0.08
     війсь
    0.08
     трей
    0.08
     सैन
    0.08
     reminding
    0.08
    �
    0.08
    Activations Density 0.003%

    No Known Activations