© 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. 23-RESID-POST-AA
    11. 97723
    Prev
    Next
    INDEX
    Explanations

    本文

    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
     brauchen
    -0.10
     sapere
    -0.09
     көрсету
    -0.08
     know
    -0.08
     benötigen
    -0.08
     sabotage
    -0.08
     brauchst
    -0.08
     necesitan
    -0.08
    handle
    -0.07
     cook
    -0.07
    POSITIVE LOGITS
    着
    0.14
    结合
    0.14
    从
    0.13
    力
    0.13
    從
    0.12
    围
    0.12
    立
    0.11
    首先
    0.11
    聚
    0.11
     从
    0.11
    Activations Density 0.029%

    No Known Activations