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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2495
    Prev
    Next
    INDEX
    Explanations

    linear algebra

    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
    atan
    -0.08
    _quad
    -0.08
     fashioned
    -0.08
     Balk
    -0.07
    bery
    -0.07
     والس
    -0.07
     ಸಮ
    -0.07
     barras
    -0.07
     conveyed
    -0.07
    _presence
    -0.07
    POSITIVE LOGITS
    (IC
    0.08
    0.08
     datasource
    0.08
     پ
    0.08
     ટે
    0.07
    习
    0.07
     atent
    0.07
    siz
    0.07
     germs
    0.07
    :white
    0.07
    Activations Density 0.014%

    No Known Activations