© 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. 8139
    Prev
    Next
    INDEX
    Explanations

    divisible

    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
     nies
    -0.09
     เน
    -0.08
     Idle
    -0.08
     ផ
    -0.08
     tired
    -0.08
    idle
    -0.08
     ryd
    -0.07
     الخار
    -0.07
    Idle
    -0.07
     ngoài
    -0.07
    POSITIVE LOGITS
    性愛
    0.08
     بالفعل
    0.07
     wykony
    0.07
     perfectamente
    0.07
    ято
    0.07
    ฝ
    0.07
     perfeitamente
    0.07
    -arm
    0.07
    ర్చ
    0.07
    �
    0.07
    Activations Density 0.016%

    No Known Activations