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. 90063
    Prev
    Next
    INDEX
    Explanations

    analyze

    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
    rown
    -0.09
     Poverty
    -0.08
     المست
    -0.08
    Stayed
    -0.08
    Costo
    -0.07
    美元
    -0.07
    rare
    -0.07
    ambiar
    -0.07
     Té
    -0.07
    Longitude
    -0.07
    POSITIVE LOGITS
     ATS
    0.09
     নজ
    0.09
     юу
    0.08
    gest
    0.08
     लक्ष
    0.08
     punishment
    0.08
     sexual
    0.08
     halluc
    0.07
     NC
    0.07
     gro
    0.07
    Activations Density 0.020%

    No Known Activations