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. 65091
    Prev
    Next
    INDEX
    Explanations

    hands

    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
     needs
    -0.09
    respond
    -0.08
     terminology
    -0.07
    ئ
    -0.07
     Needs
    -0.07
     몇
    -0.07
     notation
    -0.07
    电
    -0.07
     (↵↵
    -0.07
     Nicholas
    -0.07
    POSITIVE LOGITS
     запрещ
    0.08
    /items
    0.08
     удоволь
    0.08
    せ
    0.08
    う
    0.08
     sollicit
    0.08
     behalve
    0.08
    スク
    0.08
     laug
    0.07
     renda
    0.07
    Activations Density 0.005%

    No Known Activations