© 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. 44816
    Prev
    Next
    INDEX
    Explanations

    actual vs unofficial

    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
     dones
    -0.09
     Gallagher
    -0.08
     бах
    -0.08
     тэх
    -0.08
     Maw
    -0.08
     maso
    -0.08
     chví
    -0.08
    urrender
    -0.08
    otron
    -0.08
     গান
    -0.08
    POSITIVE LOGITS
     unofficial
    0.20
     informal
    0.18
     undocumented
    0.11
     facto
    0.10
    implicitly
    0.09
     trotzdem
    0.09
     dennoch
    0.09
    implicit
    0.09
     anyway
    0.09
     implicit
    0.09
    Activations Density 0.197%

    No Known Activations