Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88024
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    UTES
    -0.09
    ండ
    -0.08
    ух
    -0.08
    	
    -0.08
    ंटी
    -0.07
     अगर
    -0.07
    ``.↵↵
    -0.07
    /
    -0.07
    ンド
    -0.07
    ਨਾਂ
    -0.07
    POSITIVE LOGITS
     inherently
    0.08
     WPA
    0.08
     oluline
    0.08
    oleum
    0.08
     corretamente
    0.08
     directe
    0.08
     palindrome
    0.08
     desej
    0.08
    amana
    0.08
    lestick
    0.07
    Activations Density 0.150%

    No Known Activations