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. 88019
    Prev
    Next
    INDEX
    Explanations

    parallax

    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
     germ
    -0.08
     andro
    -0.08
     Radical
    -0.07
     carpet
    -0.07
    corn
    -0.07
    con
    -0.07
     codec
    -0.07
    日至
    -0.07
    ensin
    -0.07
     چى
    -0.07
    POSITIVE LOGITS
    (link
    0.09
     מנ
    0.08
     규모
    0.08
    Wt
    0.08
     मल
    0.07
    体验
    0.07
    $link
    0.07
     pressão
    0.07
     وراء
    0.07
     lei
    0.07
    Activations Density 0.001%

    No Known Activations