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. 12249
    Prev
    Next
    INDEX
    Explanations

    LEFT

    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
     punk
    -0.08
    +x
    -0.08
     fellows
    -0.08
     lähe
    -0.08
     jsx
    -0.07
    stations
    -0.07
    ствием
    -0.07
     ök
    -0.07
     coexist
    -0.07
    (js
    -0.07
    POSITIVE LOGITS
     Jahr
    0.09
     century
    0.09
     मध
    0.08
    'année
    0.08
     distint
    0.08
     mim
    0.08
     रह
    0.08
     मध्ये
    0.08
     শত
    0.08
     مص
    0.08
    Activations Density 0.002%

    No Known Activations