© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6409
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     se
    -0.08
     estimates
    -0.07
    And
    -0.07
    B
    -0.07
     triggers
    -0.07
     B
    -0.07
    ons
    -0.07
     sea
    -0.07
    U
    -0.07
     And
    -0.07
    POSITIVE LOGITS
     wohnhaft
    0.09
    ござ
    0.09
     ịhụ
    0.09
     kuitenkaan
    0.09
     DAMAGES
    0.09
    éanmoins
    0.09
     דווקא
    0.09
     Бірақ
    0.09
     למרות
    0.09
     نفت
    0.09
    Activations Density 0.000%

    No Known Activations