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. 130531
    Prev
    Next
    INDEX
    Explanations

    a

    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
    ansi
    -0.09
    Identity
    -0.08
    etu
    -0.08
    그리고
    -0.08
     constants
    -0.08
     overarching
    -0.07
     enlightening
    -0.07
     foundational
    -0.07
     proliferation
    -0.07
     identities
    -0.07
    POSITIVE LOGITS
     Asking
    0.08
     الفنية
    0.08
     أنحاء
    0.08
     Probate
    0.07
     Berg
    0.07
     عالية
    0.07
     Retrieval
    0.07
     Assisted
    0.07
     Joseph
    0.07
     مباشرة
    0.07
    Activations Density 0.031%

    No Known Activations