© 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. 110306
    Prev
    Next
    INDEX
    Explanations

    Google Translate

    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
    募
    -0.09
     probation
    -0.09
     Coron
    -0.08
     apron
    -0.08
    发行
    -0.08
    (menu
    -0.08
    March
    -0.08
    (metadata
    -0.08
     exam
    -0.07
     bosses
    -0.07
    POSITIVE LOGITS
     multilingual
    0.12
    .languages
    0.12
     Translator
    0.12
     traduction
    0.12
    .translation
    0.11
    .Translate
    0.11
     tradução
    0.11
    _translate
    0.11
     translators
    0.10
     translator
    0.10
    Activations Density 0.009%

    No Known Activations