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. 55925
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
     künftig
    -0.09
     када
    -0.09
     PDE
    -0.09
     Kala
    -0.08
     mín
    -0.08
     calendrier
    -0.08
     invierno
    -0.08
     desa
    -0.08
    erlukan
    -0.08
     Sturm
    -0.08
    POSITIVE LOGITS
     attendees
    0.10
     convivial
    0.09
     decorations
    0.09
     iedereen
    0.09
    欢乐
    0.09
     весел
    0.09
     mingle
    0.09
     Guests
    0.09
     guests
    0.09
     roam
    0.09
    Activations Density 0.107%

    No Known Activations