© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1299
    Prev
    Next
    INDEX
    Explanations

    不上

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recount
    -0.08
     ऑन
    -0.07
     relat
    -0.07
     spesielt
    -0.07
     spelling
    -0.07
     History
    -0.07
     ontsp
    -0.07
     Extrem
    -0.07
     predis
    -0.07
     Partial
    -0.07
    POSITIVE LOGITS
     tilted
    0.08
     infra
    0.08
    Katie
    0.08
     Rin
    0.08
    hf
    0.08
    asio
    0.07
    Gef
    0.07
    gig
    0.07
     aspiration
    0.07
    шы
    0.07
    Activations Density 0.001%

    No Known Activations