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. 104191
    Prev
    Next
    INDEX
    Explanations

    kidding

    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
    -France
    -0.09
    .Feature
    -0.08
     استقبال
    -0.08
     Funnel
    -0.08
    south
    -0.07
     Funnels
    -0.07
     funnel
    -0.07
     Fonction
    -0.07
    浓
    -0.07
    ovolj
    -0.07
    POSITIVE LOGITS
     prank
    0.09
     swear
    0.09
     crazy
    0.08
     sérieux
    0.08
     เล่น
    0.08
     nonsense
    0.08
     outfit
    0.08
     kwijt
    0.08
     😂
    0.08
     bedo
    0.08
    Activations Density 0.029%

    No Known Activations