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. 101352
    Prev
    Next
    INDEX
    Explanations

    us

    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
    Speech
    -0.08
    Mesh
    -0.07
    Cube
    -0.07
    Billing
    -0.07
    -0.07
    =========
    -0.07
    Training
    -0.07
    Money
    -0.07
     bear
    -0.07
    ging
    -0.07
    POSITIVE LOGITS
     clásicos
    0.09
     Презид
    0.08
    displaystyle
    0.08
     Seja
    0.08
     Rockefeller
    0.08
     klasik
    0.08
     вида
    0.08
     समी
    0.08
     PBS
    0.08
     oherwydd
    0.08
    Activations Density 0.004%

    No Known Activations