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. 54424
    Prev
    Next
    INDEX
    Explanations

    art and symbolism

    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
     babys
    -0.09
     commander
    -0.08
     smartest
    -0.08
     santa
    -0.08
     annoying
    -0.08
     governor
    -0.08
    ഴിക്ക
    -0.08
     confirmation
    -0.08
     batteries
    -0.08
    Commander
    -0.08
    POSITIVE LOGITS
     reminiscent
    0.11
    -inspired
    0.10
     depicting
    0.10
    Palette
    0.10
     sculptures
    0.09
     inspired
    0.09
     homage
    0.09
     haunting
    0.09
     sculpture
    0.09
    _palette
    0.09
    Activations Density 0.095%

    No Known Activations