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. 112767
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    Sz
    -0.08
     aang
    -0.08
     hole
    -0.07
     gut
    -0.07
     Sz
    -0.07
     sz
    -0.07
    elly
    -0.07
    \">\
    -0.07
     shifted
    -0.07
     ती
    -0.07
    POSITIVE LOGITS
    Composite
    0.08
     Northern
    0.08
    .store
    0.08
     someday
    0.08
     �
    0.08
    /self
    0.08
     Australians
    0.07
    _UPLOAD
    0.07
    Reached
    0.07
     Composite
    0.07
    Activations Density 0.001%

    No Known Activations