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. 103055
    Prev
    Next
    INDEX
    Explanations

    zombies/undead

    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
     administered
    -0.07
     Ф
    -0.07
    -0.07
     manipul
    -0.07
     allant
    -0.07
    лив
    -0.07
    	Block
    -0.07
    -unused
    -0.07
    hether
    -0.07
    787
    -0.07
    POSITIVE LOGITS
     advogado
    0.08
     നിയമ
    0.08
     kert
    0.08
     eky
    0.08
     juridique
    0.08
     Lawyer
    0.08
    icer
    0.08
     peor
    0.07
     pior
    0.07
    此同时
    0.07
    Activations Density 0.003%

    No Known Activations