© 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. 52162
    Prev
    Next
    INDEX
    Explanations

    movement toward

    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
     joke
    -0.09
     stoj
    -0.08
     mitu
    -0.08
     üks
    -0.08
     jpeg
    -0.08
     ruas
    -0.08
     ibi
    -0.08
     Jag
    -0.08
     Extended
    -0.08
     uitgebreide
    -0.08
    POSITIVE LOGITS
     towards
    0.27
     toward
    0.26
     hacia
    0.20
    tow
    0.17
     Towards
    0.17
    Towards
    0.17
     نحو
    0.15
     Tow
    0.15
    Tow
    0.15
     away
    0.14
    Activations Density 0.052%

    No Known Activations