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. 43179
    Prev
    Next
    INDEX
    Explanations

    内容

    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
     Moon
    -0.08
     asp
    -0.08
     Dead
    -0.07
    冷
    -0.07
     trolls
    -0.07
    Dead
    -0.07
     പ്രശ
    -0.07
    ovac
    -0.07
     chilling
    -0.07
    Blocked
    -0.07
    POSITIVE LOGITS
     banyere
    0.09
    默
    0.09
     Samb
    0.09
     salient
    0.08
     Sir
    0.08
     essent
    0.07
     babagan
    0.07
    録
    0.07
    SSC
    0.07
     Cari
    0.07
    Activations Density 0.008%

    No Known Activations