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. 9004
    Prev
    Next
    INDEX
    Explanations

    batteries

    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
    �
    -0.08
     sof
    -0.08
     poisson
    -0.08
     مناطق
    -0.08
     здійс
    -0.08
     بسر
    -0.08
     feem
    -0.08
     risiko
    -0.08
     stond
    -0.07
     rischio
    -0.07
    POSITIVE LOGITS
     batteries
    0.09
     Ur
    0.09
    Ur
    0.09
     fizz
    0.09
     Gute
    0.08
     Akk
    0.08
     Batteries
    0.08
     Akku
    0.08
     batería
    0.08
    gn
    0.08
    Activations Density 0.004%

    No Known Activations