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. 15-RESID-POST-AA
    6. 8
    Prev
    Next
    INDEX
    Explanations

    Invented words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يزال
    -0.09
     تزال
    -0.08
    .Column
    -0.08
    یکار
    -0.08
     ബന്ധപ്പെട്ട
    -0.08
    	Page
    -0.08
     సంబంధ
    -0.08
     учащ
    -0.08
     espalda
    -0.08
    _Should
    -0.08
    POSITIVE LOGITS
    ™
    0.10
     combines
    0.08
     Invent
    0.08
     pun
    0.08
    pun
    0.08
     fusion
    0.08
    comb
    0.08
    fusion
    0.08
    invent
    0.08
     serious
    0.08
    Activations Density 0.116%

    No Known Activations