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. 54307
    Prev
    Next
    INDEX
    Explanations

    access

    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
    Invite
    -0.09
     Loh
    -0.09
     militar
    -0.08
    ùng
    -0.08
     hunter
    -0.08
    ụtara
    -0.08
     требованиям
    -0.08
    满
    -0.08
    Genre
    -0.08
     commissioned
    -0.08
    POSITIVE LOGITS
     accessing
    0.16
     accessed
    0.15
    访问
    0.14
     accesses
    0.14
     acessar
    0.14
    アクセス
    0.13
     acceder
    0.12
     Zugriff
    0.12
    access
    0.12
     accéder
    0.11
    Activations Density 0.028%

    No Known Activations