Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 12081
    Prev
    Next
    INDEX
    Explanations

    Superlative adjectives and adverbs

    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
     vasos
    -0.09
     сул
    -0.08
     neki
    -0.08
     invita
    -0.08
     kiasi
    -0.08
     odpow
    -0.08
     ий
    -0.08
     ilg
    -0.08
     Kool
    -0.08
     kwaye
    -0.08
    POSITIVE LOGITS
     Children's
    0.08
    tl
    0.08
    (||
    0.07
    (reference
    0.07
     언
    0.07
    <|reserved_200016|>
    0.07
    tenham
    0.07
    ichannel
    0.07
     mq
    0.07
    cross
    0.07
    Activations Density 0.044%

    No Known Activations