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. 15-RESID-POST-AA
    6. 91
    Prev
    Next
    INDEX
    Explanations

    say shape

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichael
    -0.09
     신규
    -0.09
    馨
    -0.08
     доступа
    -0.08
     soa
    -0.08
    IKA
    -0.08
     PSA
    -0.08
     psa
    -0.08
     최초
    -0.08
     ilkin
    -0.08
    POSITIVE LOGITS
     sturd
    0.16
     sturdy
    0.15
     withstand
    0.15
     resistentes
    0.12
     stevige
    0.12
     firme
    0.12
    耐
    0.11
     resistente
    0.11
     durability
    0.11
     longer
    0.11
    Activations Density 0.011%

    No Known Activations