© 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. 11-RESID-POST-AA
    11. 54919
    Prev
    Next
    INDEX
    Explanations

    Macbeth

    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
     subscriber
    -0.09
     Subscriber
    -0.08
     recycl
    -0.08
     député
    -0.08
    ércio
    -0.08
    ensión
    -0.08
    มาย
    -0.08
    된다
    -0.08
    ystème
    -0.08
    لمي
    -0.08
    POSITIVE LOGITS
     activates
    0.08
    'U
    0.08
    .activate
    0.07
     decisive
    0.07
     desperate
    0.07
     TA
    0.07
     coordinating
    0.07
     segíts
    0.07
     exhort
    0.07
     facilitating
    0.07
    Activations Density 0.003%

    No Known Activations