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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5670
    Prev
    Next
    INDEX
    Explanations

    non-english software/data analysis

    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
    ল
    -0.08
    wt
    -0.07
     NFT
    -0.07
     Booking
    -0.07
     Depos
    -0.07
     shit
    -0.07
     filled
    -0.07
    લા
    -0.07
     stunning
    -0.07
     Internationale
    -0.07
    POSITIVE LOGITS
    اف
    0.10
     облег
    0.09
     skole
    0.08
     keter
    0.08
    ியான
    0.08
     افزار
    0.08
     ades
    0.08
    مند
    0.08
    MAKE
    0.08
     educ
    0.08
    Activations Density 0.000%

    No Known Activations