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. 11579
    Prev
    Next
    INDEX
    Explanations

    code

    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
     therap
    -0.07
     $('#'
    -0.07
     preceded
    -0.07
     plunged
    -0.07
    :auto
    -0.07
    ocked
    -0.07
     terapeut
    -0.07
     therapy
    -0.07
     sewage
    -0.07
    icais
    -0.07
    POSITIVE LOGITS
     accumulating
    0.18
     accum
    0.18
     acumul
    0.17
     accumulate
    0.17
     accumulation
    0.17
    Accum
    0.16
    Accumulator
    0.15
     accumulator
    0.15
     накоп
    0.15
     collecting
    0.14
    Activations Density 0.032%

    No Known Activations