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. 106180
    Prev
    Next
    INDEX
    Explanations

    legal negation

    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
    ugno
    -0.09
     Runde
    -0.08
     rück
    -0.08
     Fakten
    -0.08
     Uy
    -0.07
    UX
    -0.07
     Ursula
    -0.07
     XXL
    -0.07
     Muk
    -0.07
     ASEAN
    -0.07
    POSITIVE LOGITS
    applications
    0.08
     estaciones
    0.08
    Graduate
    0.08
     city's
    0.08
    crease
    0.08
     estacion
    0.07
    」,
    0.07
    Division
    0.07
    Salida
    0.07
     it'll
    0.07
    Activations Density 0.012%

    No Known Activations