© 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. 20847
    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
    -many
    -0.12
     অনেক
    -0.11
    much
    -0.11
     wiele
    -0.11
    many
    -0.11
     viele
    -0.11
     багато
    -0.11
    -use
    -0.10
     więcej
    -0.10
     mnoho
    -0.10
    POSITIVE LOGITS
     as
    0.09
     volledige
    0.09
     maupun
    0.09
     buong
    0.08
     uniek
    0.08
     unieke
    0.08
     unique
    0.08
     Ook
    0.08
     деталей
    0.08
     relevant
    0.08
    Activations Density 0.004%

    No Known Activations