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. 45842
    Prev
    Next
    INDEX
    Explanations

    bc

    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
     vehe
    -0.08
     initiating
    -0.07
     Thirty
    -0.07
    ]<<
    -0.07
    Vak
    -0.07
     Vaughan
    -0.07
    $username
    -0.07
    над
    -0.07
     Anglican
    -0.07
    ,var
    -0.07
    POSITIVE LOGITS
     이해
    0.08
     متعدد
    0.08
     मौजूद
    0.08
    基础
    0.08
    ೊಂದಿಗೆ
    0.07
     transversal
    0.07
     हिस्सा
    0.07
     जानकारी
    0.07
     समझ
    0.07
    idors
    0.07
    Activations Density 0.026%

    No Known Activations