© 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. 63134
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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
    assle
    -0.09
     "\\
    -0.08
     reakc
    -0.08
     reaks
    -0.08
     réaction
    -0.08
    violent
    -0.07
     reaction
    -0.07
     реак
    -0.07
    ohle
    -0.07
     [:
    -0.07
    POSITIVE LOGITS
     обход
    0.09
     pon
    0.08
    (flow
    0.08
    大会
    0.08
     devenir
    0.08
    歩
    0.07
     долго
    0.07
    フ
    0.07
    leness
    0.07
     Wak
    0.07
    Activations Density 0.002%

    No Known Activations