© 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. 19787
    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
     understanding
    -0.10
     понять
    -0.09
     Demonstr
    -0.09
     zapew
    -0.08
     સમજ
    -0.08
     IO
    -0.08
     demonstration
    -0.08
    �ย
    -0.08
     поним
    -0.08
     I
    -0.08
    POSITIVE LOGITS
     have
    0.12
     hebben
    0.11
     necesariamente
    0.11
     entonces
    0.10
     hayan
    0.10
     necessarily
    0.10
     इसलिए
    0.10
     necessariamente
    0.10
     forcément
    0.10
     allora
    0.10
    Activations Density 0.027%

    No Known Activations