© 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. 52081
    Prev
    Next
    INDEX
    Explanations

    Sunscreens and UV protection

    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
    READ
    -0.08
    decimal
    -0.08
     interior
    -0.08
    spam
    -0.08
     interiores
    -0.08
    _decimal
    -0.08
     fox
    -0.07
    akeng
    -0.07
     Remote
    -0.07
     combating
    -0.07
    POSITIVE LOGITS
     biso
    0.09
     av
    0.09
    Av
    0.09
     Av
    0.09
     sulis
    0.08
     hom
    0.08
    -av
    0.08
    Ij
    0.07
     असर
    0.07
     Dias
    0.07
    Activations Density 0.001%

    No Known Activations