© 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. 23-RESID-POST-AA
    11. 50837
    Prev
    Next
    INDEX
    Explanations

    Math computations

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تص
    -0.08
     dispute
    -0.08
     championship
    -0.08
    Σ
    -0.07
    μμ
    -0.07
     nhà
    -0.07
    İN
    -0.07
    Old
    -0.07
    �
    -0.07
    Bei
    -0.07
    POSITIVE LOGITS
     Kail
    0.08
     revelou
    0.08
     Rush
    0.08
     تقوم
    0.07
    (adapter
    0.07
     admir
    0.07
    agonal
    0.07
     Folge
    0.07
    aries
    0.07
    687
    0.07
    Activations Density 0.001%

    No Known Activations