© 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. 70107
    Prev
    Next
    INDEX
    Explanations

    Video encoding/color formats

    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
     Vermont
    -0.09
     presos
    -0.08
     Veteran
    -0.08
     پرس
    -0.08
     recycler
    -0.08
     Chemicals
    -0.08
     Spirits
    -0.08
     Waziri
    -0.08
    aschen
    -0.08
     Haunted
    -0.08
    POSITIVE LOGITS
    面积
    0.09
     rectangular
    0.09
     scopes
    0.08
    cc
    0.08
    尺寸
    0.08
    Distrib
    0.08
    サイズ
    0.08
    Director
    0.08
     volledige
    0.08
    umfang
    0.08
    Activations Density 0.002%

    No Known Activations