© 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. 31017
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ಾಖ
    -0.08
    Abr
    -0.08
     halka
    -0.07
     upang
    -0.07
     recog
    -0.07
     pusat
    -0.07
    ાખ
    -0.07
     aron
    -0.07
    -cent
    -0.07
    乾
    -0.07
    POSITIVE LOGITS
     👍
    0.08
    -virus
    0.08
     :-)
    0.08
     पार्ट
    0.08
    👍
    0.08
     🙂
    0.08
    terior
    0.08
     😊
    0.07
    ously
    0.07
    одно
    0.07
    Activations Density 0.020%

    No Known Activations