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. 12258
    Prev
    Next
    INDEX
    Explanations

    onian

    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
     gait
    -0.09
    /job
    -0.09
     adequ
    -0.09
    /support
    -0.08
    walking
    -0.08
     cleavage
    -0.08
     wangu
    -0.08
     গেছে
    -0.07
     verb
    -0.07
     yangu
    -0.07
    POSITIVE LOGITS
     circles
    0.09
     trees
    0.09
    carousel
    0.08
    trees
    0.08
    circle
    0.08
     evangel
    0.08
     forests
    0.08
    _circle
    0.08
     Trees
    0.07
     είτε
    0.07
    Activations Density 0.004%

    No Known Activations