© 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. 52199
    Prev
    Next
    INDEX
    Explanations

    Rivers in India

    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
     rivier
    -0.11
     creek
    -0.10
     canal
    -0.10
     river
    -0.09
     River
    -0.09
     नदी
    -0.09
     waterways
    -0.09
    Village
    -0.08
     নদ
    -0.08
    Streams
    -0.08
    POSITIVE LOGITS
    恒
    0.10
     恒
    0.10
     G
    0.08
     Yam
    0.08
     mechanical
    0.08
    SON
    0.08
    机械
    0.08
    _IGNORE
    0.07
     mechanically
    0.07
    科技
    0.07
    Activations Density 0.002%

    No Known Activations