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. 15-RESID-POST-AA
    6. 18925
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -'
    -0.09
    -Б
    -0.09
    -links
    -0.09
    +:
    -0.09
    -react
    -0.09
    -B
    -0.08
    -Re
    -0.08
    -R
    -0.08
    -ons
    -0.08
    -Se
    -0.08
    POSITIVE LOGITS
     kanilang
    0.11
     kanyang
    0.09
     multitude
    0.09
     pagkakata
    0.09
     country's
    0.09
     aşağı
    0.08
     world's
    0.08
     nation's
    0.08
     application's
    0.08
     game's
    0.08
    Activations Density 0.053%

    No Known Activations