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. 117534
    Prev
    Next
    INDEX
    Explanations

    Local IP addresses

    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
     Ferm
    -0.09
     Know
    -0.08
     Lind
    -0.08
     Perse
    -0.08
     arriving
    -0.08
     الله
    -0.08
     Vir
    -0.07
     abak
    -0.07
    وصل
    -0.07
    little
    -0.07
    POSITIVE LOGITS
     operational
    0.09
    Operational
    0.08
     Operational
    0.08
     air
    0.08
     följ
    0.08
     constat
    0.08
     malesuada
    0.08
     soy
    0.08
     vlan
    0.07
     mott
    0.07
    Activations Density 0.001%

    No Known Activations