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. 120083
    Prev
    Next
    INDEX
    Explanations

    times

    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
    Wild
    -0.08
     animations
    -0.08
     éventuellement
    -0.08
    wild
    -0.08
     Leaf
    -0.08
    Pic
    -0.07
     Wild
    -0.07
     Stored
    -0.07
    Mal
    -0.07
     Mal
    -0.07
    POSITIVE LOGITS
     nữa
    0.09
    (inplace
    0.08
    /be
    0.08
     americano
    0.07
     cape
    0.07
    以内
    0.07
     внут
    0.07
    争霸
    0.07
    �
    0.07
     américains
    0.07
    Activations Density 0.015%

    No Known Activations