© 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. 11-RESID-POST-AA
    11. 63239
    Prev
    Next
    INDEX
    Explanations

    Time zones

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     matric
    -0.09
    .Style
    -0.08
     leitor
    -0.08
     loto
    -0.08
     груди
    -0.08
     minlength
    -0.08
     guarant
    -0.08
     auctor
    -0.08
     encouraged
    -0.08
     sq
    -0.08
    POSITIVE LOGITS
    Timezone
    0.11
     UTC
    0.10
     east
    0.10
    east
    0.10
     timezone
    0.09
     clock
    0.09
    (city
    0.09
     reloj
    0.09
     గంట
    0.09
     മണിക്ക
    0.09
    Activations Density 0.007%

    No Known Activations