Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12002
    Prev
    Next
    INDEX
    Explanations

    relationships between items

    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
    สง
    -0.09
    -ish
    -0.09
     الدنيا
    -0.08
    �
    -0.07
    alts
    -0.07
    -Aug
    -0.07
     Yang
    -0.07
     ändern
    -0.07
     elegant
    -0.07
     vuel
    -0.07
    POSITIVE LOGITS
     הזה
    0.08
     correspondiente
    0.08
    年代
    0.08
    ين
    0.08
     terce
    0.07
     الخاص
    0.07
    ующий
    0.07
     Machado
    0.07
    時計
    0.07
     aged
    0.07
    Activations Density 0.085%

    No Known Activations