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. 46556
    Prev
    Next
    INDEX
    Explanations

    hyper

    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
    31
    -0.08
    34
    -0.07
     dizaine
    -0.07
    ungi
    -0.07
    .↵↵
    -0.07
     composition
    -0.07
     thirty
    -0.07
     loyalty
    -0.07
    						  
    -0.07
    66
    -0.07
    POSITIVE LOGITS
    plots
    0.09
     extremists
    0.09
     asym
    0.08
    joen
    0.08
     !)
    0.08
    \">\
    0.08
     развод
    0.08
    ירן
    0.08
     Uiteindelijk
    0.08
     pól
    0.08
    Activations Density 0.018%

    No Known Activations