© 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. 50861
    Prev
    Next
    INDEX
    Explanations

    whether

    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
     жүрген
    -0.09
    ғанда
    -0.09
     donde
    -0.09
     tür
    -0.08
     Where
    -0.08
     iştir
    -0.08
     алғаш
    -0.08
    ¿Qué
    -0.08
    जह
    -0.08
     bulunan
    -0.08
    POSITIVE LOGITS
     there's
    0.16
    /how
    0.15
     there
    0.15
     it's
    0.15
     they
    0.14
     they'll
    0.13
     you're
    0.13
     anyone
    0.12
     they're
    0.12
     any
    0.12
    Activations Density 0.096%

    No Known Activations