© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 102341
    Prev
    Next
    INDEX
    Explanations

    Override

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cumprimento
    -0.09
     الاحتلال
    -0.09
    [this
    -0.09
    ,this
    -0.09
    、この
    -0.09
     таъмин
    -0.09
    anlage
    -0.09
    these
    -0.08
    ליך
    -0.08
    Israel
    -0.08
    POSITIVE LOGITS
     cross
    0.10
    (@
    0.09
    _cross
    0.09
     @
    0.09
    ದು
    0.08
     vient
    0.08
     rooted
    0.07
     Cross
    0.07
    ross
    0.07
    -cross
    0.07
    Activations Density 0.000%

    No Known Activations