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. 49115
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     deform
    -0.08
    ONE
    -0.08
    ilere
    -0.08
    asten
    -0.08
    ingredient
    -0.08
    Ingredients
    -0.08
    imb
    -0.07
     असे
    -0.07
    lements
    -0.07
     TIM
    -0.07
    POSITIVE LOGITS
    ออนไลน์
    0.08
     besucht
    0.08
     онлайн
    0.08
     verk
    0.08
     kommun
    0.08
     bahasa
    0.07
     là
    0.07
     конс
    0.07
    DS
    0.07
     Cabr
    0.07
    Activations Density 0.113%

    No Known Activations