© 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. 103401
    Prev
    Next
    INDEX
    Explanations

    say "cup"

    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
     structures
    -0.10
     Structures
    -0.10
     היא
    -0.09
     estructura
    -0.09
    Structure
    -0.09
    -Line
    -0.09
     estructuras
    -0.09
    .false
    -0.08
     Struktur
    -0.08
    Structures
    -0.08
    POSITIVE LOGITS
    杯
    0.15
     cup
    0.15
     كوب
    0.15
     чаш
    0.14
     taza
    0.13
     cups
    0.13
    盒彩
    0.12
    컵
    0.12
     стак
    0.12
    cup
    0.11
    Activations Density 0.008%

    No Known Activations