© 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. 102395
    Prev
    Next
    INDEX
    Explanations

    say intersection

    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
     "
    -0.09
     `
    -0.08
     {
    -0.08
     not
    -0.08
    ,
    -0.07
     Dev
    -0.07
     estar
    -0.07
     compute
    -0.07
     calcular
    -0.07
    ર્ક
    -0.07
    POSITIVE LOGITS
    -components
    0.10
     sämt
    0.09
     interchangeable
    0.09
     அனை
    0.09
     সমস্ত
    0.09
    Endpoints
    0.09
     wszystkich
    0.09
     всеми
    0.08
     Eintritt
    0.08
     successive
    0.08
    Activations Density 0.007%

    No Known Activations