© 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. 91477
    Prev
    Next
    INDEX
    Explanations

    verifying calculations

    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
    .layers
    -0.09
    /th
    -0.08
     اپ
    -0.08
    ニュー
    -0.08
    꿈
    -0.08
     cortex
    -0.08
    .cells
    -0.08
    /extensions
    -0.08
    apollo
    -0.07
     ನೆ
    -0.07
    POSITIVE LOGITS
     qualifies
    0.09
    	valid
    0.09
    验证
    0.09
     funktioniert
    0.08
     geprü
    0.08
    牛
    0.08
     confirms
    0.08
     palindrome
    0.08
     identifies
    0.08
     evidently
    0.07
    Activations Density 0.069%

    No Known Activations