© 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. 19-RESID-POST-AA
    11. 103135
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     THAT
    -0.09
     that
    -0.09
     Mult
    -0.08
    .Multi
    -0.08
    	that
    -0.08
     Multi
    -0.08
    that
    -0.07
    .Mult
    -0.07
    َن
    -0.07
     FOOT
    -0.07
    POSITIVE LOGITS
     પોતાની
    0.10
     કેટલીક
    0.09
     સામાન્ય
    0.08
     бумаги
    0.08
     кожу
    0.08
     જિલ્લાના
    0.08
     eigene
    0.08
     જિલ્લા
    0.08
    સર
    0.08
     кожи
    0.08
    Activations Density 0.010%

    No Known Activations