© 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. 30089
    Prev
    Next
    INDEX
    Explanations

    LAB

    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
     नीति
    -0.09
     mirando
    -0.08
     अब
    -0.08
     सेवा
    -0.08
    与此同时
    -0.08
     hizmet
    -0.07
     अनुमति
    -0.07
    数据显示
    -0.07
     प्रतियोग
    -0.07
     إذ
    -0.07
    POSITIVE LOGITS
    Rollback
    0.09
    ורך
    0.08
    rollment
    0.08
    օ
    0.07
    ø
    0.07
    Raid
    0.07
    btc
    0.07
    Conse
    0.07
     terken
    0.07
    awu
    0.07
    Activations Density 0.000%

    No Known Activations