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. 9109
    Prev
    Next
    INDEX
    Explanations

    simmer

    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
     हाल
    -0.09
     NIL
    -0.08
    έα
    -0.08
     arbeids
    -0.08
     पु
    -0.08
    .Measure
    -0.08
     आव
    -0.08
     व्यक्ति
    -0.07
    .normal
    -0.07
     Engineering
    -0.07
    POSITIVE LOGITS
     patiently
    0.09
    cord
    0.07
    ili
    0.07
     cord
    0.07
    stitute
    0.07
    暑
    0.07
    (cam
    0.07
    Mor
    0.07
     chats
    0.07
     arqu
    0.07
    Activations Density 0.002%

    No Known Activations