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. 65766
    Prev
    Next
    INDEX
    Explanations

    intensive care

    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
     delim
    -0.08
     hemp
    -0.08
    ardown
    -0.07
     טובה
    -0.07
    �
    -0.07
    .inst
    -0.07
     Eigent
    -0.07
     CER
    -0.07
    転
    -0.07
     подт
    -0.07
    POSITIVE LOGITS
    fps
    0.09
     ventil
    0.09
     cockpit
    0.08
     tty
    0.08
    Phil
    0.08
     intensiv
    0.08
     porto
    0.08
    anejo
    0.08
     instrumentation
    0.08
     kaff
    0.07
    Activations Density 0.005%

    No Known Activations