© 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. 3-RESID-POST-AA
    11. 12886
    Prev
    Next
    INDEX
    Explanations

    r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     બધ
    -0.07
     alerted
    -0.07
     stimulated
    -0.07
     Tre
    -0.07
    这里只
    -0.07
     જગ્ય
    -0.07
     transferred
    -0.07
    _tree
    -0.07
     Aguil
    -0.07
    .clicked
    -0.07
    POSITIVE LOGITS
     bood
    0.08
     crush
    0.08
     Dylan
    0.07
    .du
    0.07
     ata
    0.07
     repose
    0.07
     stroll
    0.07
     nate
    0.07
     bloqueo
    0.07
     pomag
    0.07
    Activations Density 0.004%

    No Known Activations