© 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. 1447
    Prev
    Next
    INDEX
    Explanations

    potassium

    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
     acad
    -0.08
     acadêm
    -0.08
     原
    -0.08
     قلت
    -0.08
    сом
    -0.08
     Regierungs
    -0.07
     remarked
    -0.07
     КП
    -0.07
     �
    -0.07
     ала
    -0.07
    POSITIVE LOGITS
     प्रभावित
    0.08
    nutrition
    0.08
    倾
    0.08
    AN
    0.08
    Magento
    0.07
    nof
    0.07
    FTP
    0.07
     loyal
    0.07
    ாத்த
    0.07
    irq
    0.07
    Activations Density 0.001%

    No Known Activations