© 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. 65445
    Prev
    Next
    INDEX
    Explanations

    USB

    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
    (proxy
    -0.08
    /general
    -0.08
    .async
    -0.08
     aplikasyon
    -0.08
     Zul
    -0.08
     عنصر
    -0.07
     flim
    -0.07
     lone
    -0.07
    (attribute
    -0.07
     ʻia
    -0.07
    POSITIVE LOGITS
    	DEBUG
    0.08
     поддерж
    0.07
    ીઠ
    0.07
     BID
    0.07
    atanga
    0.07
    opped
    0.07
     режим
    0.07
    art
    0.07
     PAD
    0.07
     ketosis
    0.07
    Activations Density 0.001%

    No Known Activations