© 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. 20627
    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
     cualquier
    -0.07
     bdsm
    -0.07
    utada
    -0.07
     ejempl
    -0.07
     énergétique
    -0.07
    alla
    -0.07
    argar
    -0.07
     allan
    -0.07
     dsp
    -0.07
    -0.07
    POSITIVE LOGITS
     respectivos
    0.12
     respectivas
    0.12
     corresponding
    0.12
    分别
    0.11
     entsprechenden
    0.11
     respective
    0.11
     Beide
    0.11
     beide
    0.11
     entsprechend
    0.11
     correspondientes
    0.10
    Activations Density 0.012%
    No Known Activations