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. 130281
    Prev
    Next
    INDEX
    Explanations

    ive

    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
     francs
    -0.08
     roja
    -0.08
     hypoc
    -0.08
    ONS
    -0.07
     appelle
    -0.07
     honn
    -0.07
     Parijs
    -0.07
     sena
    -0.07
     Observation
    -0.07
     Spir
    -0.07
    POSITIVE LOGITS
     predictive
    0.13
     trending
    0.10
    趋势
    0.10
     analytics
    0.10
    Trending
    0.09
     tendencias
    0.09
     tendances
    0.09
     forecasting
    0.09
     วิเคราะห์
    0.09
     actionable
    0.09
    Activations Density 0.007%

    No Known Activations