Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130852
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    display
    -0.09
     display
    -0.08
    .run
    -0.08
    python
    -0.07
    “M
    -0.07
    Barr
    -0.07
    ms
    -0.07
    disc
    -0.07
    M
    -0.07
    Mr
    -0.07
    POSITIVE LOGITS
     ಒ
    0.07
     kiosk
    0.07
     aggreg
    0.07
    け
    0.07
     ova
    0.07
     LH
    0.07
     určit
    0.07
     निश्चित
    0.07
     ovo
    0.07
     ٹھ
    0.07
    Activations Density 0.016%

    No Known Activations