Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 97101
    Prev
    Next
    INDEX
    Explanations

    say "gives"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     causing
    -0.14
     causando
    -0.14
    adds
    -0.13
     helping
    -0.13
    allows
    -0.12
     Enables
    -0.12
     Allows
    -0.12
    Adds
    -0.12
     Helps
    -0.12
    Allows
    -0.12
    POSITIVE LOGITS
     produced
    0.11
     deliver
    0.10
    给
    0.10
     given
    0.10
     ارائه
    0.09
     delivered
    0.09
    y
    0.09
    g
    0.09
     Ou
    0.09
     give
    0.09
    Activations Density 0.110%

    No Known Activations