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. 3-RESID-POST-AA
    6. 1863
    Prev
    Next
    INDEX
    Explanations

    website URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ्चर
    -0.08
    isio
    -0.08
     Gloucester
    -0.08
     alk
    -0.08
     Alk
    -0.07
    ाकार
    -0.07
    iso
    -0.07
    LOS
    -0.07
     epi
    -0.07
    iellement
    -0.07
    POSITIVE LOGITS
    /~
    0.07
     Shelf
    0.07
     Kra
    0.07
    ,这是
    0.07
     fil
    0.07
     Brid
    0.07
    ಯ್ಯ
    0.07
    .staff
    0.07
    wel
    0.07
    phan
    0.07
    Activations Density 0.025%

    No Known Activations