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. 58315
    Prev
    Next
    INDEX
    Explanations

    DE

    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
     Hunter
    -0.09
     कप
    -0.07
     Média
    -0.07
    Kin
    -0.07
    (op
    -0.07
     chronique
    -0.07
    тона
    -0.07
    plex
    -0.07
    coop
    -0.07
    .w
    -0.07
    POSITIVE LOGITS
     отправ
    0.08
     исполнения
    0.08
    etud
    0.08
     �
    0.08
     выполнение
    0.08
    Send
    0.08
    さん
    0.07
    ]_
    0.07
     millionaire
    0.07
    男子
    0.07
    Activations Density 0.212%

    No Known Activations