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. 49824
    Prev
    Next
    INDEX
    Explanations

    kiwi

    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
     मेरी
    -0.08
     monaster
    -0.08
     limites
    -0.07
     academ
    -0.07
     undergo
    -0.07
     cavern
    -0.07
     cylinder
    -0.07
     dele
    -0.07
     zdecyd
    -0.07
     stochastic
    -0.07
    POSITIVE LOGITS
    型
    0.09
    物流
    0.09
    Produit
    0.08
    笑
    0.08
     breeze
    0.08
    ossal
    0.08
    ikon
    0.08
    Passport
    0.08
     rhin
    0.07
    nut
    0.07
    Activations Density 0.001%

    No Known Activations