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. 113048
    Prev
    Next
    INDEX
    Explanations

    mood

    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
    த
    -0.08
    .optional
    -0.08
     Uch
    -0.07
     Pueblo
    -0.07
     Kuz
    -0.07
    ל
    -0.07
     Vog
    -0.07
     Dek
    -0.07
     Donec
    -0.07
     Schulen
    -0.07
    POSITIVE LOGITS
     depressive
    0.08
    态
    0.08
     العام
    0.08
     Stimmung
    0.08
     Depression
    0.08
     depression
    0.08
     upbeat
    0.08
     nt
    0.08
    アップ
    0.08
     saff
    0.08
    Activations Density 0.014%

    No Known Activations