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. 65202
    Prev
    Next
    INDEX
    Explanations

    elections and voting

    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
     energie
    -0.09
    MY
    -0.08
    enes
    -0.08
     secretion
    -0.08
    Energy
    -0.07
     worsen
    -0.07
     Ducati
    -0.07
    energie
    -0.07
    「あ
    -0.07
     yoga
    -0.07
    POSITIVE LOGITS
     ballot
    0.17
     ভোট
    0.15
     ballots
    0.15
     electoral
    0.15
     voter
    0.15
     मतदान
    0.13
     தேர்த
    0.13
     partisan
    0.13
     ಮತ
    0.13
     ಚುನಾವಣ
    0.13
    Activations Density 0.049%

    No Known Activations