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. 90141
    Prev
    Next
    INDEX
    Explanations

    a

    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
    ermen
    -0.09
    ownika
    -0.08
     clasp
    -0.08
     meni
    -0.08
     dient
    -0.08
     achten
    -0.08
     Ornament
    -0.08
    enal
    -0.08
    -0.08
     имеется
    -0.08
    POSITIVE LOGITS
     glossy
    0.09
     더욱
    0.09
    hero
    0.08
     hassle
    0.08
     truly
    0.08
    Overview
    0.08
    安心
    0.08
    .quick
    0.08
     snug
    0.08
    更
    0.08
    Activations Density 0.039%

    No Known Activations