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. 60590
    Prev
    Next
    INDEX
    Explanations

    fighting evil in fantasy

    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
    Follow
    -0.09
     intentionally
    -0.08
    ēm
    -0.08
    _follow
    -0.08
    follow
    -0.08
     gevolgd
    -0.08
    .follow
    -0.08
    leven
    -0.07
    न्ह
    -0.07
     Monopoly
    -0.07
    POSITIVE LOGITS
     threatens
    0.08
     strapped
    0.08
     Can't
    0.08
     पर्व
    0.08
     looming
    0.08
    ்
    0.08
    ์
    0.08
     Foundation
    0.07
     threaten
    0.07
    燃
    0.07
    Activations Density 0.035%

    No Known Activations