© 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. 19-RESID-POST-AA
    11. 19120
    Prev
    Next
    INDEX
    Explanations

    Legal language

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imamo
    -0.08
     nuevos
    -0.08
     figuring
    -0.08
     personali
    -0.08
     jambes
    -0.08
     seeing
    -0.07
     vivimos
    -0.07
     pensamos
    -0.07
     nuovi
    -0.07
     vemos
    -0.07
    POSITIVE LOGITS
     shall
    0.15
     hereby
    0.14
     agrees
    0.14
     shalt
    0.11
     يجوز
    0.11
     Shall
    0.10
     acknowledges
    0.10
     recommends
    0.10
     advises
    0.10
     acuer
    0.10
    Activations Density 0.003%

    No Known Activations