Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19603
    Prev
    Next
    INDEX
    Explanations

    block

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     herum
    -0.08
     modifies
    -0.07
    جيب
    -0.07
    UME
    -0.07
    urg
    -0.07
     Tile
    -0.07
    ంలోని
    -0.07
    _wrapper
    -0.07
    chemy
    -0.07
    ريان
    -0.07
    POSITIVE LOGITS
    ,同比增长
    0.10
     sebanyak
    0.09
    次数
    0.09
    /sec
    0.09
    前年比
    0.09
     respectable
    0.08
    率
    0.08
     sprint
    0.08
     sizeable
    0.08
     decent
    0.08
    Activations Density 0.015%

    No Known Activations