Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11835
    Prev
    Next
    INDEX
    Explanations

    toothpick grids

    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
     roast
    -0.09
     romance
    -0.08
    投
    -0.08
    يغ
    -0.08
    ult
    -0.08
     exile
    -0.07
     wilderness
    -0.07
    ಿಯ
    -0.07
     lyrics
    -0.07
    erialized
    -0.07
    POSITIVE LOGITS
     Econ
    0.08
     વી
    0.08
     benötigt
    0.08
     perpendicular
    0.08
    bahn
    0.08
     gerade
    0.08
     लागत
    0.08
     resistor
    0.08
     বল
    0.08
     сооруж
    0.08
    Activations Density 0.012%

    No Known Activations