© 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. 78505
    Prev
    Next
    INDEX
    Explanations

    system

    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
    ځ
    -0.08
     Qt
    -0.08
     Ministries
    -0.08
     einst
    -0.08
     soldados
    -0.07
     Offices
    -0.07
     Chineke
    -0.07
     Süden
    -0.07
     Navy
    -0.07
    obod
    -0.07
    POSITIVE LOGITS
     dimensão
    0.09
     combinations
    0.08
     chose
    0.08
     demographics
    0.08
    Kul
    0.08
    송
    0.08
     safari
    0.08
     device
    0.08
    	type
    0.08
    型号
    0.07
    Activations Density 0.009%

    No Known Activations