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. 60634
    Prev
    Next
    INDEX
    Explanations

    Continuing stories/scenes

    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
    కి
    -0.08
    权益
    -0.08
     koya
    -0.08
     uds
    -0.08
     большую
    -0.08
     gaat
    -0.07
    测速
    -0.07
    有所
    -0.07
    利益
    -0.07
    Constr
    -0.07
    POSITIVE LOGITS
    llen
    0.08
     abruptly
    0.08
     etc
    0.08
     mies
    0.08
     halted
    0.08
     reconc
    0.07
    Last
    0.07
    venth
    0.07
    pens
    0.07
     pendent
    0.07
    Activations Density 0.019%

    No Known Activations