© 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. 3-RESID-POST-AA
    11. 2872
    Prev
    Next
    INDEX
    Explanations

    three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.10
     യോഗ
    -0.08
    谈
    -0.08
    .grp
    -0.08
    Adv
    -0.08
    മ
    -0.08
    談
    -0.07
    诉
    -0.07
     struck
    -0.07
    ovor
    -0.07
    POSITIVE LOGITS
    Cre
    0.09
    )],↵
    0.08
     rigu
    0.08
    чен
    0.07
    чно
    0.07
     unfinished
    0.07
    }],↵
    0.07
    /Re
    0.07
     проиг
    0.07
    }]↵
    0.07
    Activations Density 0.004%

    No Known Activations