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. 87909
    Prev
    Next
    INDEX
    Explanations

    ое

    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
    .orm
    -0.08
     boilers
    -0.08
     renovate
    -0.08
     balances
    -0.08
     Affero
    -0.08
     renovating
    -0.08
     Powers
    -0.08
     SWOT
    -0.08
     scholarships
    -0.08
     Lic
    -0.08
    POSITIVE LOGITS
    mousedown
    0.13
     joystick
    0.13
    gesture
    0.12
     tactile
    0.12
    Mouse
    0.12
    	mouse
    0.12
    Joystick
    0.12
     mouse
    0.12
    (mouse
    0.12
     gesture
    0.12
    Activations Density 0.007%

    No Known Activations