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. 44254
    Prev
    Next
    INDEX
    Explanations

    on

    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
     voorkomende
    -0.07
     dividends
    -0.07
     uranium
    -0.07
    >>>>>>>
    -0.07
     bear
    -0.07
    .dimension
    -0.07
    Почему
    -0.07
    edata
    -0.07
    .identifier
    -0.07
     spores
    -0.07
    POSITIVE LOGITS
     mnie
    0.08
     плеч
    0.08
     doorstep
    0.08
    ────────────────
    0.07
     લઈ
    0.07
     tem
    0.07
    桌
    0.07
     берег
    0.07
     нашей
    0.07
    ોટ
    0.07
    Activations Density 0.019%

    No Known Activations