© 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. 54748
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     earthquakes
    -0.07
    /Post
    -0.07
     Bernard
    -0.07
    ennig
    -0.07
    Emotion
    -0.07
     Tren
    -0.07
    Founded
    -0.07
     Internet
    -0.07
    Mounted
    -0.07
    Connections
    -0.07
    POSITIVE LOGITS
     consequently
    0.09
    سے
    0.08
    სახ
    0.08
     fixed
    0.08
    fixed
    0.08
    -ste
    0.08
    kje
    0.08
    pụta
    0.08
     accordingly
    0.08
     السعر
    0.08
    Activations Density 0.199%

    No Known Activations