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. 109055
    Prev
    Next
    INDEX
    Explanations

    linear regulators

    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
    Dere
    -0.08
    usr
    -0.08
     SPI
    -0.08
    ুল
    -0.07
    -to
    -0.07
     absent
    -0.07
     نظر
    -0.07
     �
    -0.07
     Spart
    -0.07
    POSITIVE LOGITS
     hart
    0.09
     χει
    0.08
     destroying
    0.08
    WEST
    0.08
     transporting
    0.07
    .toolbox
    0.07
     inaad
    0.07
     Karin
    0.07
    console
    0.07
    west
    0.07
    Activations Density 0.001%

    No Known Activations