© 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. 52280
    Prev
    Next
    INDEX
    Explanations

    SOLID design principles

    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
    _dec
    -0.09
     dec
    -0.09
    Mui
    -0.08
     hopped
    -0.08
     والأس
    -0.08
     arred
    -0.08
     decentral
    -0.08
     detachable
    -0.07
     мах
    -0.07
     الحض
    -0.07
    POSITIVE LOGITS
     SR
    0.16
    SR
    0.14
     SOL
    0.13
     DR
    0.12
     Don't
    0.11
     ISP
    0.11
     Dependency
    0.11
     GR
    0.11
    DR
    0.11
     Open
    0.11
    Activations Density 0.003%

    No Known Activations