© 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. 51917
    Prev
    Next
    INDEX
    Explanations

    Mentions research institutions

    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
    fills
    -0.08
    ἐ
    -0.08
    ્
    -0.08
     chewing
    -0.07
    \Common
    -0.07
     Releases
    -0.07
     Taller
    -0.07
     acud
    -0.07
    
    -0.07
    apay
    -0.07
    POSITIVE LOGITS
     there's
    0.08
     j
    0.08
     scramble
    0.07
     안정
    0.07
    [j
    0.07
     бө
    0.07
    -laws
    0.07
     javax
    0.07
     jig
    0.07
     landed
    0.07
    Activations Density 0.001%

    No Known Activations