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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99300
    Prev
    Next
    INDEX
    Explanations

    Turing machines

    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
     basil
    -0.08
     مخت
    -0.08
     Серг
    -0.07
    estrutura
    -0.07
    herent
    -0.07
     alt
    -0.07
     Christoph
    -0.07
     meur
    -0.07
     erectile
    -0.07
     тарт
    -0.07
    POSITIVE LOGITS
     piles
    0.09
     DE
    0.08
    .operation
    0.08
     deposits
    0.08
     tableau
    0.08
    .ones
    0.08
    blank
    0.07
     depositing
    0.07
     Blank
    0.07
     Fact
    0.07
    Activations Density 0.002%

    No Known Activations