© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 114342
    Prev
    Next
    INDEX
    Explanations

    от

    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
    ton
    -0.09
     affluent
    -0.08
    Background
    -0.07
    澡
    -0.07
    ucleus
    -0.07
     olímp
    -0.07
    	background
    -0.07
     savent
    -0.07
     εργ
    -0.07
     konsep
    -0.07
    POSITIVE LOGITS
     зависит
    0.15
     залеж
    0.15
     afhankelijk
    0.15
     depending
    0.15
    Depending
    0.14
     dependant
    0.14
     Depending
    0.14
     abhängig
    0.13
     зависимости
    0.13
    depends
    0.13
    Activations Density 0.051%

    No Known Activations