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. 90459
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
    weiler
    -0.09
     Purchased
    -0.09
     BCE
    -0.08
    leyo
    -0.08
     Applicable
    -0.08
     Epis
    -0.08
     преб
    -0.08
     hohen
    -0.08
    Applicable
    -0.08
    =tk
    -0.08
    POSITIVE LOGITS
     science
    0.08
     bio
    0.08
    bio
    0.08
     ethic
    0.08
     video
    0.07
     Claudia
    0.07
     transmit
    0.07
     hap
    0.07
    Tx
    0.07
    Twitter
    0.07
    Activations Density 0.019%

    No Known Activations