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. 65160
    Prev
    Next
    INDEX
    Explanations

    disk partitioning

    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
     wick
    -0.08
     Vector
    -0.08
     logist
    -0.08
     eil
    -0.08
    helle
    -0.08
     Renderer
    -0.08
     groei
    -0.08
     Morales
    -0.08
    折
    -0.07
     Nahrung
    -0.07
    POSITIVE LOGITS
     चीन
    0.08
    ahid
    0.08
    Owner
    0.08
     چین
    0.08
    Foreign
    0.08
    UUID
    0.08
     propietarios
    0.08
    Owners
    0.08
    atai
    0.08
    Bg
    0.07
    Activations Density 0.002%

    No Known Activations