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. 111794
    Prev
    Next
    INDEX
    Explanations

    differentiation and levels

    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
     إجراء
    -0.08
    Sac
    -0.08
     amash
    -0.08
     uth
    -0.08
     capp
    -0.07
    お問い合わせ
    -0.07
    atha
    -0.07
     Fran
    -0.07
    عی
    -0.07
    Contacto
    -0.07
    POSITIVE LOGITS
     catered
    0.12
    everyone
    0.10
    Everyone
    0.10
     wszystkim
    0.10
     accommodates
    0.09
     adults
    0.09
     caters
    0.09
     Senioren
    0.09
     accommodated
    0.09
     adaptés
    0.09
    Activations Density 0.051%

    No Known Activations