© 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. 65354
    Prev
    Next
    INDEX
    Explanations

    marching

    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
    Owned
    -0.09
    Ownership
    -0.08
    -owner
    -0.08
    Merchant
    -0.08
    741
    -0.08
    Entity
    -0.08
    owned
    -0.07
    fram
    -0.07
    Ctx
    -0.07
    League
    -0.07
    POSITIVE LOGITS
     embar
    0.08
    stay
    0.08
     hyster
    0.08
    噜
    0.08
     nutt
    0.08
     evolucion
    0.08
    prechen
    0.08
    嘴
    0.07
     acerc
    0.07
     feas
    0.07
    Activations Density 0.004%

    No Known Activations