© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47797
    Prev
    Next
    INDEX
    Explanations

    speech

    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
     tablero
    -0.08
     charts
    -0.07
     निश्चित
    -0.07
    截至
    -0.07
     learn
    -0.07
     koy
    -0.07
     mapa
    -0.07
     mecanismo
    -0.07
     خاص
    -0.07
     garantir
    -0.07
    POSITIVE LOGITS
     whispered
    0.12
    说道
    0.11
     aloud
    0.10
     apolog
    0.10
     apology
    0.10
     spoken
    0.10
     말했다
    0.10
     echoed
    0.10
    maals
    0.09
     verbally
    0.09
    Activations Density 0.064%

    No Known Activations