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. 43168
    Prev
    Next
    INDEX
    Explanations

    ynthetic

    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
     boxer
    -0.09
     Box
    -0.09
     listing
    -0.08
     Dumpster
    -0.08
     Pantry
    -0.08
     gái
    -0.08
     kvalit
    -0.08
     Boxer
    -0.07
    ربع
    -0.07
     sirve
    -0.07
    POSITIVE LOGITS
    Intensity
    0.10
     activity
    0.10
     intensity
    0.09
     ઝડપ
    0.09
    .capacity
    0.09
    .activity
    0.09
     maxim
    0.09
     વધારે
    0.09
    _activity
    0.09
     활
    0.09
    Activations Density 0.003%

    No Known Activations