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. 102761
    Prev
    Next
    INDEX
    Explanations

    Escape character for period

    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
     उत
    -0.09
    خر
    -0.08
     Kak
    -0.08
     nagp
    -0.08
    מים
    -0.08
    resent
    -0.08
    êmica
    -0.08
     Speakers
    -0.07
     Presenter
    -0.07
     inert
    -0.07
    POSITIVE LOGITS
     processed
    0.08
    clean
    0.07
     considere
    0.07
     �
    0.07
    label
    0.07
     passado
    0.07
     Ltd
    0.07
    Sized
    0.07
     BLACK
    0.07
     regexp
    0.07
    Activations Density 0.004%

    No Known Activations