© 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. 210
    Prev
    Next
    INDEX
    Explanations

    Nonsensical humor/fictional stories

    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
    ENDED
    -0.08
    ��
    -0.08
    ("[%
    -0.08
     որևէ
    -0.08
     установлен
    -0.08
    الی
    -0.08
     indicado
    -0.07
     ڪا
    -0.07
    Пос
    -0.07
     MQ
    -0.07
    POSITIVE LOGITS
    !
    0.08
     socks
    0.08
     tweets
    0.08
    屁股
    0.08
    -themed
    0.08
    nit
    0.08
    袜
    0.08
    nog
    0.07
     pizzas
    0.07
     pancakes
    0.07
    Activations Density 0.165%

    No Known Activations