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. 109757
    Prev
    Next
    INDEX
    Explanations

    flesh

    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
    ging
    -0.08
     reorder
    -0.07
     whether
    -0.07
     Hanoi
    -0.07
     depends
    -0.07
     designing
    -0.07
    ios
    -0.07
     Davenport
    -0.07
    리가
    -0.07
    ľ
    -0.07
    POSITIVE LOGITS
     incarn
    0.14
     incarnation
    0.12
     embodiment
    0.11
     embodiments
    0.11
     humana
    0.10
     humaine
    0.10
     scripture
    0.09
     الإنسانية
    0.09
     avat
    0.09
     flesh
    0.09
    Activations Density 0.008%

    No Known Activations