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. 112436
    Prev
    Next
    INDEX
    Explanations

    too

    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
     zuges
    -0.08
     Franz
    -0.08
    (for
    -0.08
    ANCED
    -0.08
    TD
    -0.08
     tapered
    -0.08
    язан
    -0.07
     tailored
    -0.07
     ориент
    -0.07
    hausen
    -0.07
    POSITIVE LOGITS
     wol
    0.09
    pilot
    0.09
    wolf
    0.08
    wner
    0.08
     dangerously
    0.08
    0.07
     wolf
    0.07
     Ski
    0.07
     ski
    0.07
     faker
    0.07
    Activations Density 0.014%

    No Known Activations