© 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. 22783
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     murdering
    -0.09
    .lwjgl
    -0.08
     prerequisite
    -0.08
    Newton
    -0.08
    .RESULT
    -0.08
     prerequisites
    -0.08
     malfunction
    -0.08
    wein
    -0.08
    ２
    -0.08
    ::_('
    -0.07
    POSITIVE LOGITS
     reach
    0.13
     crescita
    0.13
     croissance
    0.12
     crescimento
    0.12
     uniques
    0.12
     growth
    0.12
     رشد
    0.11
     groei
    0.11
    增长
    0.11
    ，同比增长
    0.11
    Activations Density 0.004%

    No Known Activations