Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 76102
    Prev
    Next
    INDEX
    Explanations

    guarantee

    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
     оказалось
    -0.08
    Mv
    -0.08
    hold
    -0.08
    汉
    -0.07
    ъв
    -0.07
     другом
    -0.07
    bomb
    -0.07
    graduate
    -0.07
    orch
    -0.07
    candidate
    -0.07
    POSITIVE LOGITS
     guarantees
    0.09
    rl
    0.09
     warranties
    0.08
     Garantie
    0.08
    保証
    0.08
     garantías
    0.08
     guaranteed
    0.08
    Guarante
    0.08
    ર
    0.08
     indoor
    0.07
    Activations Density 0.007%

    No Known Activations