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. 74704
    Prev
    Next
    INDEX
    Explanations

    Russian regulatory agencies

    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
     Chip
    -0.08
     όλα
    -0.08
     sustainability
    -0.08
    Chip
    -0.08
    န်း
    -0.07
     Sustainability
    -0.07
     começam
    -0.07
    лення
    -0.07
     iwu
    -0.07
     alterações
    -0.07
    POSITIVE LOGITS
     affectionate
    0.08
     gastronom
    0.08
     cousins
    0.08
    Observers
    0.07
     stud
    0.07
    itors
    0.07
    那个
    0.07
     SOB
    0.07
     Pond
    0.07
    dess
    0.07
    Activations Density 0.001%

    No Known Activations