Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9095
    Prev
    Next
    INDEX
    Explanations

    code

    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
    _FIFO
    -0.08
     electronically
    -0.07
    truction
    -0.07
    Pak
    -0.07
    URL
    -0.07
    祭
    -0.07
     மர
    -0.07
    Hall
    -0.07
    estroy
    -0.07
     EMP
    -0.07
    POSITIVE LOGITS
     трен
    0.08
    rauch
    0.08
     приобрет
    0.07
     wi
    0.07
     Chlor
    0.07
    	do
    0.07
     छथि
    0.07
     amet
    0.07
     blazer
    0.07
     перес
    0.07
    Activations Density 0.001%

    No Known Activations