© 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. 19-RESID-POST-AA
    11. 22216
    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
     keskust
    -0.10
    ाळ
    -0.09
    ुवार
    -0.09
    alim
    -0.09
     değerlend
    -0.08
    τικότητα
    -0.08
    िकल
    -0.08
     anumang
    -0.08
     kultura
    -0.08
     qualsevol
    -0.08
    POSITIVE LOGITS
    ８
    0.09
    source
    0.08
    _Source
    0.08
     so
    0.08
    ៨
    0.08
    .source
    0.08
    8
    0.08
    源
    0.07
    _SOURCE
    0.07
    ૮
    0.07
    Activations Density 0.013%

    No Known Activations