© 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. 51640
    Prev
    Next
    INDEX
    Explanations

    cloths and wipes

    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
     Seattle
    -0.08
    Saturday
    -0.08
     enterr
    -0.08
    地下
    -0.08
    ursday
    -0.08
     anchors
    -0.08
     Saturday
    -0.08
     plomberie
    -0.08
    IGGER
    -0.08
     Anchorage
    -0.07
    POSITIVE LOGITS
     doek
    0.15
     microfiber
    0.15
     cloth
    0.15
     khăn
    0.15
     wipe
    0.14
     wipes
    0.13
     tissues
    0.13
     قطعة
    0.13
     wiping
    0.13
     wiped
    0.13
    Activations Density 0.023%

    No Known Activations