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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 131048
    Prev
    Next
    INDEX
    Explanations

    fourth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ancora
    -0.08
     hebben
    -0.08
     ponder
    -0.08
     avoir
    -0.07
    -max
    -0.07
    naa
    -0.07
    -grow
    -0.07
     Ile
    -0.07
     aver
    -0.07
    zon
    -0.07
    POSITIVE LOGITS
    spir
    0.08
    evaluation
    0.08
    蜘蛛
    0.08
     malignant
    0.08
    oarthritis
    0.08
     Exit
    0.07
     Entrada
    0.07
     windshield
    0.07
     traurig
    0.07
    airie
    0.07
    Activations Density 0.004%

    No Known Activations