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. 8992
    Prev
    Next
    INDEX
    Explanations

    Paste

    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
     �
    -0.09
     tourn
    -0.08
     നായ
    -0.08
     argentino
    -0.08
     Díaz
    -0.08
     �
    -0.07
    canon
    -0.07
     supervised
    -0.07
     ¡
    -0.07
    namespace
    -0.07
    POSITIVE LOGITS
     skin
    0.10
    Skin
    0.09
     Skin
    0.09
     skincare
    0.09
     Painter
    0.09
     moisturizing
    0.08
    পূর্ণ
    0.08
    েশ
    0.08
     staining
    0.08
     oly
    0.08
    Activations Density 0.001%

    No Known Activations