© 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. 99343
    Prev
    Next
    INDEX
    Explanations

    mixed

    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
    blur
    -0.09
     Jean
    -0.08
     Buddha
    -0.08
    .vertx
    -0.08
     believing
    -0.08
     gran
    -0.07
     granular
    -0.07
    Jean
    -0.07
    ctx
    -0.07
     soja
    -0.07
    POSITIVE LOGITS
     ટકા
    0.08
     disguise
    0.08
     ugly
    0.08
    ી�
    0.08
     хуш
    0.08
    stücke
    0.08
    121
    0.08
     dhib
    0.08
     nasty
    0.08
     lakh
    0.08
    Activations Density 0.001%

    No Known Activations