© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 21503
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     potential
    -0.08
     لیکن
    -0.08
     امیدوار
    -0.08
     achievable
    -0.08
     જેથી
    -0.08
     leva
    -0.08
     même
    -0.08
     שזה
    -0.07
    Isso
    -0.07
     gebeuren
    -0.07
    POSITIVE LOGITS
     Ocean
    0.08
    said
    0.08
     বলা
    0.08
     amore
    0.08
    hale
    0.07
    ১৭
    0.07
     halv
    0.07
    Albert
    0.07
    ktober
    0.07
    ammed
    0.07
    Activations Density 0.008%

    No Known Activations