© 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. 50478
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Publishing
    -0.10
     Retrieves
    -0.09
    Printing
    -0.09
    Drama
    -0.08
     Encryption
    -0.08
    幕
    -0.08
    Issued
    -0.08
    ندگی
    -0.08
     Printing
    -0.08
     liquidation
    -0.08
    POSITIVE LOGITS
     cob
    0.12
     skillet
    0.09
     Cob
    0.09
     cuchar
    0.09
     fork
    0.09
     COB
    0.09
     grill
    0.08
    azy
    0.08
     gr
    0.08
     stove
    0.08
    Activations Density 0.002%

    No Known Activations