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. 65969
    Prev
    Next
    INDEX
    Explanations

    degree

    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
     besides
    -0.08
     psychologically
    -0.08
     psych
    -0.07
     role
    -0.07
     wünsche
    -0.07
     psicológico
    -0.07
     filesystem
    -0.07
     psychological
    -0.07
    Unnamed
    -0.07
     psychiatric
    -0.07
    POSITIVE LOGITS
     honored
    0.09
    ono
    0.09
     onvoldoende
    0.09
    limited
    0.09
     klachten
    0.08
     maximaal
    0.08
     makah
    0.08
     недостат
    0.08
     surpresa
    0.08
     behandeld
    0.08
    Activations Density 0.009%

    No Known Activations