© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75799
    Prev
    Next
    INDEX
    Explanations

    verse, us

    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
     Luck
    -0.08
    लाइन
    -0.08
    उ
    -0.08
    थ
    -0.08
     linens
    -0.08
    ಥ
    -0.08
     इलेक्ट्र
    -0.08
    terminal
    -0.08
    प
    -0.08
     मंदिर
    -0.08
    POSITIVE LOGITS
    Often
    0.09
     Girl
    0.08
    Usually
    0.08
     Usually
    0.08
     girl
    0.08
     Girls
    0.08
     storytelling
    0.08
    .prevent
    0.08
     Typically
    0.07
    قة
    0.07
    Activations Density 0.002%

    No Known Activations