© 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. 75474
    Prev
    Next
    INDEX
    Explanations

    narrative

    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
     instrumental
    -0.09
     Christus
    -0.08
    thr
    -0.08
     Thr
    -0.08
    elf
    -0.08
    word
    -0.08
    tha
    -0.08
    ovs
    -0.08
    instrument
    -0.08
    ilk
    -0.07
    POSITIVE LOGITS
     disappointing
    0.09
    打不开
    0.09
     discrepancies
    0.09
    “No
    0.09
    404
    0.08
     Jay
    0.08
     disappointed
    0.08
     unable
    0.08
     troubleshooting
    0.08
    无法
    0.08
    Activations Density 0.138%

    No Known Activations