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. 90277
    Prev
    Next
    INDEX
    Explanations

    do

    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
     subtil
    -0.08
    (tt
    -0.08
    Fixtures
    -0.07
    .cm
    -0.07
    562
    -0.07
     কারণে
    -0.07
    enzen
    -0.07
     pity
    -0.07
     obesity
    -0.07
    .flink
    -0.07
    POSITIVE LOGITS
     Except
    0.08
     التج
    0.08
     Visitor
    0.08
     Ambassador
    0.08
     Gong
    0.08
     Ravi
    0.08
    artment
    0.08
     Rechn
    0.08
    ängen
    0.08
     éx
    0.08
    Activations Density 0.002%

    No Known Activations