© 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. 2623
    Prev
    Next
    INDEX
    Explanations

    DLL

    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
     katu
    -0.09
     ابت
    -0.08
    .topic
    -0.08
     propos
    -0.08
     Sujet
    -0.08
     Kiwi
    -0.08
     topic
    -0.07
    .Shapes
    -0.07
     Zhang
    -0.07
     Topic
    -0.07
    POSITIVE LOGITS
    DLL
    0.08
    n't
    0.08
    名
    0.08
    cdecl
    0.07
    卸
    0.07
     Hollywood
    0.07
    δέ
    0.07
     payouts
    0.07
     DLL
    0.07
    -cross
    0.07
    Activations Density 0.009%

    No Known Activations