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. 9122
    Prev
    Next
    INDEX
    Explanations

    peer review and collaboration

    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
     Cary
    -0.08
     Temperature
    -0.08
     Operations
    -0.08
     ધર
    -0.08
     pulses
    -0.08
     occult
    -0.07
    岳
    -0.07
    Temperature
    -0.07
     manufacturer
    -0.07
     casinos
    -0.07
    POSITIVE LOGITS
     rubric
    0.10
     classmates
    0.09
     평가
    0.09
    teacher
    0.09
    评价
    0.09
     제출
    0.09
     ಸಲ್ಲ
    0.09
     avaliação
    0.09
     Saves
    0.09
    save
    0.08
    Activations Density 0.012%

    No Known Activations