© 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. 51967
    Prev
    Next
    INDEX
    Explanations

    cucumbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ಪರ
    -0.08
     elé
    -0.08
     Registrar
    -0.08
     appliquer
    -0.08
     discus
    -0.08
     ロ
    -0.08
     instaur
    -0.07
     Relay
    -0.07
    	p
    -0.07
     prender
    -0.07
    POSITIVE LOGITS
     Krishna
    0.09
     Chesapeake
    0.08
     Rao
    0.08
     Gav
    0.08
     Wilmington
    0.08
     mache
    0.08
    itsut
    0.08
     Gle
    0.08
    ije
    0.07
    ировка
    0.07
    Activations Density 0.000%

    No Known Activations