© 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. 29678
    Prev
    Next
    INDEX
    Explanations

    fuel

    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
     tranz
    -0.08
     gesto
    -0.08
    登记
    -0.08
     arrang
    -0.07
     Rings
    -0.07
    亚
    -0.07
    ாம்
    -0.07
     Hammer
    -0.07
     mmap
    -0.07
    /unit
    -0.07
    POSITIVE LOGITS
     vigor
    0.10
     imagination
    0.10
    italize
    0.10
     vitality
    0.10
     combust
    0.09
     creativity
    0.09
    -powered
    0.09
     morale
    0.09
     productivity
    0.09
    -paced
    0.09
    Activations Density 0.039%

    No Known Activations