© 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. 44923
    Prev
    Next
    INDEX
    Explanations

    meter readings

    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
    gol
    -0.08
    gun
    -0.07
    irds
    -0.07
     Ü
    -0.07
     skeleton
    -0.07
    גו
    -0.07
    songs
    -0.07
     zwaar
    -0.07
    gow
    -0.07
     busca
    -0.07
    POSITIVE LOGITS
    Recorded
    0.09
    ಾವಣೆ
    0.09
    changes
    0.08
    Watcher
    0.08
    .after
    0.08
     newer
    0.08
     snapshots
    0.08
     stimulate
    0.08
    ಾವಣ
    0.08
     Ches
    0.08
    Activations Density 0.011%

    No Known Activations