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. 78727
    Prev
    Next
    INDEX
    Explanations

    python

    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
     contactar
    -0.08
     dex
    -0.08
    Dex
    -0.08
     ವಿಶ್ವ
    -0.08
     contacter
    -0.08
     Antwerpen
    -0.08
     universally
    -0.08
     Oral
    -0.08
    ↵        
    ↵
    -0.07
     contactez
    -0.07
    POSITIVE LOGITS
     Parti
    0.08
    ंत्री
    0.08
     scanf
    0.08
    .Vector
    0.08
     рә
    0.07
    .array
    0.07
     patio
    0.07
    -style
    0.07
     effizient
    0.07
     diversi
    0.07
    Activations Density 0.004%

    No Known Activations