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. 60475
    Prev
    Next
    INDEX
    Explanations

    tag

    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
     Featuring
    -0.08
     toon
    -0.08
     حجم
    -0.08
    Featuring
    -0.08
     Online
    -0.07
    osal
    -0.07
     trova
    -0.07
    kwal
    -0.07
    ланган
    -0.07
     Makeup
    -0.07
    POSITIVE LOGITS
    _STD
    0.08
     subscribe
    0.08
     permanently
    0.07
     Буд
    0.07
     fic
    0.07
    Obrig
    0.07
     doctrine
    0.07
    chemas
    0.07
     correl
    0.07
     governance
    0.07
    Activations Density 0.002%

    No Known Activations