© 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. 3-RESID-POST-AA
    11. 2855
    Prev
    Next
    INDEX
    Explanations

    email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pist
    -0.08
    otso
    -0.08
    44
    -0.08
     espaces
    -0.08
     nett
    -0.08
     conferir
    -0.07
     tsp
    -0.07
     termes
    -0.07
    printf
    -0.07
     wrought
    -0.07
    POSITIVE LOGITS
     الإلكتروني
    0.10
    .gmail
    0.09
     inbox
    0.08
    ล์
    0.08
     address
    0.08
    /mobile
    0.08
     Accred
    0.08
     deadlines
    0.08
     cập
    0.08
     electrónico
    0.08
    Activations Density 0.053%

    No Known Activations