Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12226
    Prev
    Next
    INDEX
    Explanations

    Conversational filler and sarcasm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !」↵↵
    -0.08
     lettere
    -0.08
     !↵↵
    -0.08
     remembers
    -0.08
     Matters
    -0.08
    !↵↵
    -0.08
    !」
    -0.08
     Solid
    -0.07
     cartas
    -0.07
     procés
    -0.07
    POSITIVE LOGITS
     sarcast
    0.15
     cynical
    0.12
     artificially
    0.11
     pretending
    0.11
     falsely
    0.10
     ironically
    0.10
     knowingly
    0.10
    .fake
    0.10
     sarcas
    0.10
     intentionally
    0.09
    Activations Density 0.030%

    No Known Activations