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. 1635
    Prev
    Next
    INDEX
    Explanations

    Math fill-in-the-blanks

    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
     nepot
    -0.08
     কী
    -0.08
     Petr
    -0.08
     pral
    -0.08
     Pi
    -0.08
     ranc
    -0.08
     paul
    -0.08
    (Read
    -0.07
     Raptors
    -0.07
    Pi
    -0.07
    POSITIVE LOGITS
     ಗಳ
    0.08
    严
    0.07
     FED
    0.07
    田
    0.07
     sö
    0.07
     cervical
    0.07
    {}\
    0.07
    .am
    0.07
     olum
    0.07
    推动
    0.07
    Activations Density 0.007%

    No Known Activations