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. 112826
    Prev
    Next
    INDEX
    Explanations

    :

    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
    iye
    -0.08
    alok
    -0.08
     Ihre
    -0.08
    完
    -0.07
     Fahrzeug
    -0.07
     Schutz
    -0.07
     Mounted
    -0.07
     actualizar
    -0.07
    assle
    -0.07
     iştir
    -0.07
    POSITIVE LOGITS
     Cand
    0.09
    Exchange
    0.09
     bidders
    0.08
    Acceleration
    0.08
     Exchange
    0.08
    ਿਖ
    0.07
     mình
    0.07
    NU
    0.07
     aangekond
    0.07
     BID
    0.07
    Activations Density 0.020%

    No Known Activations