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. 11-RESID-POST-AA
    6. 12222
    Prev
    Next
    INDEX
    Explanations

    1

    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
     를
    -0.09
    ना
    -0.08
    観
    -0.08
    (return
    -0.08
    返
    -0.08
    ы
    -0.08
    support
    -0.08
    306
    -0.08
     welcomed
    -0.08
     cardiac
    -0.08
    POSITIVE LOGITS
    koliko
    0.08
     makin
    0.08
     mál
    0.08
     hecha
    0.07
     abuse
    0.07
     greed
    0.07
     Lah
    0.07
     sadar
    0.07
     faite
    0.07
     Sot
    0.07
    Activations Density 0.015%

    No Known Activations