© 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. 19-RESID-POST-AA
    11. 17922
    Prev
    Next
    INDEX
    Explanations

    Offering assistance

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     provide
    -0.10
    ivr
    -0.09
     are
    -0.09
     తెలిసిందే
    -0.09
    шілік
    -0.09
    -亚洲
    -0.09
     discuss
    -0.09
     into
    -0.08
     allow
    -0.08
     providing
    -0.08
    POSITIVE LOGITS
     решил
    0.10
    .cpp
    0.09
     vytvo
    0.08
     понял
    0.08
     skon
    0.08
     сформ
    0.08
    .failed
    0.08
     разобраться
    0.08
     dobra
    0.08
     zehn
    0.08
    Activations Density 0.001%

    No Known Activations