© 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. 19-RESID-POST-AA
    11. 102994
    Prev
    Next
    INDEX
    Explanations

    canonical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obtainable
    -0.09
    Battery
    -0.09
    Centre
    -0.09
    Bathroom
    -0.09
    Een
    -0.09
    Center
    -0.08
    cook
    -0.08
    Converter
    -0.08
    Jdbc
    -0.08
    fortune
    -0.08
    POSITIVE LOGITS
    issa
    0.08
     используются
    0.08
    其他
    0.08
     stance
    0.08
    (original
    0.08
     사용하는
    0.08
    他们
    0.08
    ization
    0.07
     आंदोलन
    0.07
    ，他们
    0.07
    Activations Density 0.000%

    No Known Activations