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. 114008
    Prev
    Next
    INDEX
    Explanations

    Genealogy

    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
     муҳим
    -0.08
    haal
    -0.08
    հ
    -0.08
    .reshape
    -0.08
     мебошанд
    -0.07
    երգ
    -0.07
     applause
    -0.07
    ելի
    -0.07
    -plugin
    -0.07
    comed
    -0.07
    POSITIVE LOGITS
     descendants
    0.13
     ancestors
    0.12
    父
    0.11
    祖
    0.11
     ancestor
    0.11
     descendant
    0.11
    墓
    0.10
     grandson
    0.10
     माता
    0.10
     progen
    0.10
    Activations Density 0.045%

    No Known Activations