© 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. 20597
    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
     عمل
    -0.08
    OLUME
    -0.08
     کمک
    -0.08
     жұмыстар
    -0.08
     ولد
    -0.07
     مدد
    -0.07
     ileti
    -0.07
     SRC
    -0.07
    \Http
    -0.07
     sok
    -0.07
    POSITIVE LOGITS
     gehe
    0.09
    antry
    0.09
     Angst
    0.09
     utilisant
    0.08
    .jackson
    0.08
    .empty
    0.08
     eröff
    0.08
    .abs
    0.08
     procéd
    0.08
     anonym
    0.08
    Activations Density 0.002%

    No Known Activations