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. 120117
    Prev
    Next
    INDEX
    Explanations

    bow

    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
    夏
    -0.08
     summer
    -0.08
     गो
    -0.08
     genom
    -0.07
     STO
    -0.07
    _gen
    -0.07
    tery
    -0.07
     glue
    -0.07
    Summer
    -0.07
    949
    -0.07
    POSITIVE LOGITS
     intolerance
    0.09
    skirts
    0.08
    stroke
    0.08
     intensity
    0.08
    <Int
    0.08
     Etern
    0.08
     repost
    0.08
     persever
    0.08
     penetr
    0.08
     Int
    0.08
    Activations Density 0.000%

    No Known Activations