© 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. 26619
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     recession
    -0.10
     onset
    -0.09
    -0.09
     pursuit
    -0.08
     يس
    -0.08
    یس
    -0.08
    裙
    -0.08
     impending
    -0.08
     wage
    -0.08
     diagnosis
    -0.07
    POSITIVE LOGITS
    Uint
    0.08
     combin
    0.08
    boj
    0.08
     бог
    0.08
     débats
    0.08
     kall
    0.08
    polis
    0.08
    	memcpy
    0.08
     alternating
    0.08
     Parlement
    0.07
    Activations Density 0.020%
    No Known Activations