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. 53788
    Prev
    Next
    INDEX
    Explanations

    mathematical logic

    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
     Barbara
    -0.08
    sons
    -0.08
    isal
    -0.07
     importantly
    -0.07
    _INTERFACE
    -0.07
    vi
    -0.07
     בב
    -0.07
    -writing
    -0.07
     interface
    -0.07
     интерф
    -0.07
    POSITIVE LOGITS
    また
    0.08
     corpos
    0.08
     किंवा
    0.08
    enha
    0.08
    Cele
    0.08
     rejecting
    0.08
    、不
    0.08
    ,也
    0.08
    	web
    0.07
    、お
    0.07
    Activations Density 0.014%

    No Known Activations