© 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. 52023
    Prev
    Next
    INDEX
    Explanations

    reaching

    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
     شرق
    -0.08
     partly
    -0.08
    _CONST
    -0.08
     mye
    -0.08
     ప్రాంత
    -0.08
     adaptés
    -0.08
     relations
    -0.07
     Relations
    -0.07
     вниз
    -0.07
    .Mapping
    -0.07
    POSITIVE LOGITS
     earliest
    0.25
     reaching
    0.21
     alcanzar
    0.20
    达到
    0.20
     reached
    0.19
     spätestens
    0.19
     reaches
    0.19
     atingir
    0.19
     atteindre
    0.19
    Reached
    0.18
    Activations Density 0.091%

    No Known Activations