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. 11749
    Prev
    Next
    INDEX
    Explanations

    musician data

    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
    ऑ
    -0.08
    ogat
    -0.08
     vermelho
    -0.07
     ऑ
    -0.07
     mathematic
    -0.07
    oplastic
    -0.07
     multinational
    -0.07
    028
    -0.07
     conception
    -0.07
    Pedro
    -0.07
    POSITIVE LOGITS
    		
    ↵
    0.08
    gekomen
    0.08
     Glow
    0.08
     tambien
    0.08
    усов
    0.08
     saja
    0.08
     durant
    0.08
    ড়িয়ে
    0.08
     wasnt
    0.08
    sth
    0.08
    Activations Density 0.011%

    No Known Activations