© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29759
    Prev
    Next
    INDEX
    Explanations

    Negative sentiment

    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
     ಇಲ್ಲ
    -0.09
     Mga
    -0.09
    anager
    -0.08
     ಘಟನೆ
    -0.08
    ’inst
    -0.08
     ಕಾರ್ಯಕ್ರಮ
    -0.08
    örer
    -0.08
     ವಿನ
    -0.08
    onts
    -0.08
     ಯಾವುದೇ
    -0.08
    POSITIVE LOGITS
     putea
    0.10
     mute
    0.08
     beton
    0.08
     supreme
    0.07
    以来
    0.07
     boosted
    0.07
    رده
    0.07
    ன்ப
    0.07
     Boo
    0.07
    ாட்ட
    0.07
    Activations Density 0.106%

    No Known Activations