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. 77351
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     médias
    -0.08
    êtes
    -0.08
    住宿
    -0.08
     obbl
    -0.08
    住宅
    -0.08
    Residential
    -0.08
    209
    -0.08
    徽
    -0.07
    undefined
    -0.07
    ospels
    -0.07
    POSITIVE LOGITS
     koi
    0.09
     Okin
    0.08
     сц
    0.08
     Bali
    0.07
     Kab
    0.07
     cena
    0.07
     плод
    0.07
     Surgeon
    0.07
    bros
    0.07
     impl
    0.07
    Activations Density 0.000%

    No Known Activations