© 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. 3-RESID-POST-AA
    11. 1478
    Prev
    Next
    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hands
    -0.08
     assimil
    -0.08
     након
    -0.08
     compensation
    -0.08
    vare
    -0.08
    표
    -0.07
     περι
    -0.07
     اد
    -0.07
     gekozen
    -0.07
     альтернатив
    -0.07
    POSITIVE LOGITS
    itaan
    0.07
     grants
    0.07
     Rag
    0.07
    .requires
    0.07
    .Requires
    0.07
    Ten
    0.07
    Requires
    0.07
     Tenant
    0.07
     grandi
    0.07
     buoy
    0.07
    Activations Density 0.000%

    No Known Activations