© 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. 71288
    Prev
    Next
    INDEX
    Explanations

    periodic table trends

    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
     giorni
    -0.09
    _BOOT
    -0.08
    Integrity
    -0.08
     integrity
    -0.08
    Telemetry
    -0.08
    Authorized
    -0.08
    .un
    -0.08
     namespace
    -0.08
    _ATTACH
    -0.08
    Dream
    -0.08
    POSITIVE LOGITS
    排序
    0.10
    ક્રમ
    0.10
     qualit
    0.10
     fenó
    0.09
     �
    0.09
     क्रम
    0.09
     comparative
    0.09
     aromatic
    0.09
    ranking
    0.09
     chemically
    0.09
    Activations Density 0.012%

    No Known Activations