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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49066
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cht
    -0.09
    chts
    -0.08
     deg
    -0.08
     Labor
    -0.08
    Fragment
    -0.08
    chte
    -0.08
    miot
    -0.08
    deg
    -0.08
    igarh
    -0.07
    _fragment
    -0.07
    POSITIVE LOGITS
    分别
    0.10
     respectively
    0.09
     respectivos
    0.08
    ு
    0.08
    값
    0.08
     respectivas
    0.08
     Override
    0.07
    ?,?,?,?,
    0.07
     respectivamente
    0.07
     ஓ
    0.07
    Activations Density 0.008%

    No Known Activations