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. 49342
    Prev
    Next
    INDEX
    Explanations

    `/`

    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
     contention
    -0.08
     casualties
    -0.08
     ndim
    -0.08
     aanbieding
    -0.07
     conn
    -0.07
     micros
    -0.07
     الوسط
    -0.07
    -years
    -0.07
     Manufacturing
    -0.07
    Conn
    -0.07
    POSITIVE LOGITS
    /@
    0.09
    :@
    0.09
     emoji
    0.08
     empathy
    0.08
     HELP
    0.08
    reload
    0.08
    Activate
    0.08
    scene
    0.08
    (@
    0.08
     *@
    0.08
    Activations Density 0.007%

    No Known Activations