© 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. 23-RESID-POST-AA
    11. 48679
    Prev
    Next
    INDEX
    Explanations

    SQL queries and optimization

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ronnie
    -0.08
    ouwen
    -0.08
    -0.07
     CN
    -0.07
    enegro
    -0.07
    164
    -0.07
    -DD
    -0.07
     başlang
    -0.07
    04
    -0.07
     meantime
    -0.07
    POSITIVE LOGITS
     hint
    0.09
    _hint
    0.09
    STRA
    0.09
    /*
    0.09
    FOR
    0.09
    [offset
    0.08
    hint
    0.08
    :*
    0.08
    :"<<
    0.08
    SIM
    0.08
    Activations Density 0.002%
    No Known Activations