© 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. 11-RESID-POST-AA
    11. 109847
    Prev
    Next
    INDEX
    Explanations

    sleep deprivation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Grass
    -0.09
    .Resource
    -0.08
     elif
    -0.08
     سبح
    -0.08
    ստ
    -0.08
     artifact
    -0.08
     sonido
    -0.08
    .or
    -0.08
    _RESOURCE
    -0.08
    _resource
    -0.08
    POSITIVE LOGITS
     compromising
    0.10
     symptoms
    0.09
    症
    0.09
     Symptoms
    0.09
     exacer
    0.09
     exacerb
    0.09
     hamp
    0.08
     Sympt
    0.08
    攻击
    0.08
     Toxic
    0.08
    Activations Density 0.010%

    No Known Activations