© 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. 23-RESID-POST-AA
    11. 6320
    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
    alted
    -0.09
     میلیارد
    -0.08
     großen
    -0.08
    erde
    -0.08
     licking
    -0.07
     walking
    -0.07
    ー
    -0.07
    èque
    -0.07
    र्मी
    -0.07
    ਕ
    -0.07
    POSITIVE LOGITS
    �
    0.14
     irrigation
    0.12
     irrig
    0.11
    �
    0.09
    渠
    0.09
    刷水
    0.09
     rainfall
    0.09
     drainage
    0.09
    圳
    0.09
    watering
    0.09
    Activations Density 0.003%

    No Known Activations