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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2655
    Prev
    Next
    INDEX
    Explanations

    )

    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
    626
    -0.07
    soil
    -0.07
     fou
    -0.07
    チェック
    -0.07
     chung
    -0.07
     �
    -0.07
     বল
    -0.07
    late
    -0.07
    729
    -0.07
    lar
    -0.07
    POSITIVE LOGITS
    Bart
    0.09
     prov
    0.09
     Catal
    0.08
     Kö
    0.08
     sæ
    0.07
     requis
    0.07
    prov
    0.07
     Bart
    0.07
     Clos
    0.07
     tandem
    0.07
    Activations Density 0.010%

    No Known Activations