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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98428
    Prev
    Next
    INDEX
    Explanations

    ध

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     đối
    -0.08
     can't
    -0.08
     CAUSED
    -0.08
    _DEVICE
    -0.08
    対
    -0.08
    can't
    -0.07
    ্ছ
    -0.07
    ഭ
    -0.07
    ിലുള്ള
    -0.07
     indispensables
    -0.07
    POSITIVE LOGITS
    ન્મ
    0.08
    avelmente
    0.08
    onderzoek
    0.08
    ોઈ
    0.08
    ಾನ್ಯ
    0.08
     Let
    0.08
    axon
    0.08
    ્વ
    0.08
    ně
    0.08
    નની
    0.08
    Activations Density 0.000%

    No Known Activations