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. 29981
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     ад
    -0.08
     Sass
    -0.07
     ц
    -0.07
    adow
    -0.07
    =_
    -0.07
     نج
    -0.07
     piled
    -0.07
     설
    -0.07
    -responsive
    -0.07
    -old
    -0.07
    POSITIVE LOGITS
     linking
    0.08
     incidente
    0.08
    comod
    0.08
    denge
    0.08
    双方
    0.08
     pairing
    0.08
     Nicht
    0.08
     �
    0.08
     չեմ
    0.07
    compute
    0.07
    Activations Density 0.018%

    No Known Activations