© 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. 23-RESID-POST-AA
    11. 51521
    Prev
    Next
    INDEX
    Explanations

    variations of "data"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     content
    -0.09
     Content
    -0.08
     code
    -0.08
     research
    -0.07
     assessments
    -0.07
    .content
    -0.07
    -0.07
     assessment
    -0.07
    ിഷ
    -0.07
    content
    -0.07
    POSITIVE LOGITS
     données
    0.29
     datos
    0.28
     dados
    0.28
     dades
    0.28
     danych
    0.27
     данных
    0.26
     Datos
    0.25
     δεδο
    0.24
     дан
    0.24
     dati
    0.24
    Activations Density 0.031%
    No Known Activations