© 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. 129523
    Prev
    Next
    INDEX
    Explanations

    Rembrandt

    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
    �
    -0.08
     Xen
    -0.08
    :X
    -0.08
     fale
    -0.07
    :P
    -0.07
    >X
    -0.07
    235
    -0.07
     imposing
    -0.07
     diagnosis
    -0.07
     xen
    -0.07
    POSITIVE LOGITS
     antiques
    0.08
    Ito
    0.08
    Bas
    0.07
     Watts
    0.07
     પા�
    0.07
     faucets
    0.07
     barna
    0.07
    aleigh
    0.07
     antique
    0.07
     Ya
    0.07
    Activations Density 0.001%

    No Known Activations