© 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. 7-RESID-POST-AA
    11. 1226
    Prev
    Next
    INDEX
    Explanations

    future dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Canadian
    -0.08
    Broad
    -0.08
     찾
    -0.08
    Dirty
    -0.07
     ضبط
    -0.07
     mistakes
    -0.07
     Broadcasting
    -0.07
     replication
    -0.07
    ֹ
    -0.07
    orted
    -0.07
    POSITIVE LOGITS
     Horizons
    0.08
     lact
    0.08
     morgen
    0.08
     Aqua
    0.08
     আগামী
    0.08
     Doha
    0.07
     pant
    0.07
     PASS
    0.07
     pelvis
    0.07
     horizons
    0.07
    Activations Density 0.007%

    No Known Activations