© 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 EvalsExportsAPI 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. 21004
    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
     involves
    -0.09
     көптеген
    -0.09
     مختلف
    -0.09
     خصوصی
    -0.09
    урх
    -0.09
     combinado
    -0.09
    maybe
    -0.08
     Verbesser
    -0.08
     personnalisé
    -0.08
     diferents
    -0.08
    POSITIVE LOGITS
    作为
    0.12
     sebagai
    0.12
     jako
    0.11
     positioned
    0.10
    成为
    0.09
    首先
    0.09
     menjadi
    0.09
     offset
    0.09
     первым
    0.08
     deline
    0.08
    Activations Density 0.003%

    No Known Activations