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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 108831
    Prev
    Next
    INDEX
    Explanations

    Random information snippets

    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
     teh
    -0.09
    ↵			↵
    -0.08
    —they
    -0.07
    �
    -0.07
    姑
    -0.07
    =sum
    -0.07
     bilden
    -0.07
    (?)
    -0.07
    Sharp
    -0.07
     grate
    -0.07
    POSITIVE LOGITS
    493
    0.08
     Arom
    0.07
    630
    0.07
     diamond
    0.07
     Unified
    0.07
     Sofa
    0.07
    ಆ
    0.07
     
    0.07
     weaken
    0.07
     Aur
    0.07
    Activations Density 0.346%

    No Known Activations