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. 11-RESID-POST-AA
    6. 61189
    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
    _adjust
    -0.08
    _modifier
    -0.08
     Cheats
    -0.08
    Modifiers
    -0.07
    _dist
    -0.07
     Mol
    -0.07
    _heat
    -0.07
    Adjustment
    -0.07
    _che
    -0.07
    _attributes
    -0.07
    POSITIVE LOGITS
    网址大全
    0.09
    чунин
    0.09
     xiy
    0.09
    备用网址
    0.09
    图片大全
    0.08
    ,国产
    0.08
    وأوضح
    0.08
    时时彩平台
    0.08
    腾讯分分彩
    0.08
    平台招商
    0.08
    Activations Density 0.007%

    No Known Activations