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. 53916
    Prev
    Next
    INDEX
    Explanations

    problem

    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
     승
    -0.08
    assis
    -0.08
     criterio
    -0.07
     questioned
    -0.07
     accl
    -0.07
    阁
    -0.07
     выс
    -0.07
     Tetapi
    -0.07
     usually
    -0.07
     použit
    -0.07
    POSITIVE LOGITS
     prevalence
    0.16
     epidemic
    0.13
     epidem
    0.12
     weltweit
    0.11
     alarming
    0.11
     epidemi
    0.11
     statistics
    0.11
     महामारी
    0.11
    全球
    0.11
     pervasive
    0.10
    Activations Density 0.120%

    No Known Activations