© 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. 31051
    Prev
    Next
    INDEX
    Explanations

    Sausages recipes and instructions

    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
     eem
    -0.09
     ee
    -0.09
     photographer
    -0.09
     prendas
    -0.08
     Optimization
    -0.08
     ફોટ
    -0.08
     fotografía
    -0.08
     Crochet
    -0.08
     Wimbledon
    -0.08
     Manhattan
    -0.08
    POSITIVE LOGITS
     fictional
    0.08
     attributes
    0.08
     sausage
    0.08
     Augustus
    0.08
    975
    0.08
     religious
    0.08
    Attributes
    0.08
     mythical
    0.07
     Attributes
    0.07
    evil
    0.07
    Activations Density 0.008%

    No Known Activations