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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 43090
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    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
     Meth
    -0.09
    Meth
    -0.09
    .optimize
    -0.09
     gokken
    -0.07
    的小
    -0.07
     optimizing
    -0.07
     calculators
    -0.07
     starring
    -0.07
    illas
    -0.07
    Optimization
    -0.07
    POSITIVE LOGITS
     Så
    0.10
     Alþ
    0.09
    cycled
    0.08
     Libre
    0.08
    Så
    0.08
     Германия
    0.08
     CUSTOM
    0.08
     aftermarket
    0.08
     séu
    0.08
     lua
    0.08
    Activations Density 0.001%

    No Known Activations