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. 58546
    Prev
    Next
    INDEX
    Explanations

    exponential growth problems

    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
     remuneration
    -0.09
    illera
    -0.08
    ")},↵
    -0.08
     remuner
    -0.08
    坐
    -0.08
     meticulous
    -0.07
    Pie
    -0.07
    bage
    -0.07
    "]}↵
    -0.07
    Misc
    -0.07
    POSITIVE LOGITS
     exponential
    0.16
     exponentially
    0.14
     doubling
    0.12
     Wachstum
    0.11
     skyrock
    0.11
     exponent
    0.10
    Dou
    0.10
     sunday
    0.10
     reaching
    0.10
    Exponent
    0.10
    Activations Density 0.034%

    No Known Activations