© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20765
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kred
    -0.08
    Correo
    -0.08
    .Email
    -0.08
     कोरोना
    -0.08
     gagal
    -0.08
     firsthand
    -0.08
    .Mail
    -0.08
     emailed
    -0.08
     содержания
    -0.08
    ,email
    -0.08
    POSITIVE LOGITS
     rounding
    0.20
     divisible
    0.20
     multiples
    0.20
     rounded
    0.19
    rounded
    0.18
     Rounded
    0.18
    nearest
    0.17
    Rounded
    0.17
    Align
    0.17
     ALIGN
    0.17
    Activations Density 0.015%

    No Known Activations