© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 13007
    Prev
    Next
    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propulsion
    -0.08
    世
    -0.07
    istert
    -0.07
    976
    -0.07
    typescript
    -0.07
     Frieden
    -0.07
    idung
    -0.07
     ush
    -0.07
    tsx
    -0.07
    jou
    -0.07
    POSITIVE LOGITS
     ஈ
    0.09
     Alk
    0.09
     मिट
    0.08
    �
    0.07
    多数
    0.07
    大会
    0.07
    碍
    0.07
    DW
    0.07
     rumm
    0.07
    Tall
    0.07
    Activations Density 0.010%

    No Known Activations