Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49159
    Prev
    Next
    INDEX
    Explanations

    standing water

    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
     upgrade
    -0.09
     Upgrade
    -0.09
    升级
    -0.09
    ಾಲಯ
    -0.08
    upgrade
    -0.08
     Byron
    -0.08
     영
    -0.08
     Acho
    -0.08
     Lou
    -0.07
     충
    -0.07
    POSITIVE LOGITS
     stagnant
    0.10
     mosquitoes
    0.08
    Anim
    0.08
    mouse
    0.08
     dangling
    0.08
     dwell
    0.08
     крови
    0.08
     mouse
    0.08
     mosquito
    0.08
     dwelling
    0.08
    Activations Density 0.005%

    No Known Activations