© 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. 635
    Prev
    Next
    INDEX
    Explanations

    human body

    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
     việc
    -0.09
     bwo
    -0.08
     欢
    -0.08
     scares
    -0.08
     размест
    -0.08
     tenis
    -0.08
     announcements
    -0.08
     announced
    -0.08
     fabul
    -0.08
     �
    -0.08
    POSITIVE LOGITS
     tissues
    0.15
     tissu
    0.11
     tissus
    0.11
     tissue
    0.11
     tejidos
    0.11
     cortex
    0.11
    ിയിലെ
    0.11
     epithelial
    0.10
     neurons
    0.10
    ocytes
    0.10
    Activations Density 0.041%

    No Known Activations