© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 16494
    Prev
    Next
    INDEX
    Explanations

    say 2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بیماری
    -0.08
     Queue
    -0.08
     محبوب
    -0.08
     مجموعه
    -0.08
     ستكون
    -0.08
    	queue
    -0.08
    чым
    -0.08
     تنزيل
    -0.08
    муля
    -0.08
    Queue
    -0.08
    POSITIVE LOGITS
     doubled
    0.10
     beiden
    0.09
     twice
    0.09
    tons
    0.08
     zweimal
    0.08
     两
    0.08
     doubles
    0.08
     beide
    0.08
    兩
    0.08
     alice
    0.08
    Activations Density 0.007%

    No Known Activations