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. 43740
    Prev
    Next
    INDEX
    Explanations

    Ganges river

    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
    .dr
    -0.08
    kung
    -0.08
     Dr
    -0.07
     teamwork
    -0.07
    SKU
    -0.07
    _dr
    -0.07
    cipher
    -0.07
    Dr
    -0.07
     braces
    -0.07
    subtotal
    -0.07
    POSITIVE LOGITS
     sacred
    0.09
     holiness
    0.09
     legality
    0.09
     revered
    0.09
    .Illegal
    0.08
     Accessibility
    0.08
     Importance
    0.08
     télécharger
    0.08
     инду
    0.08
     holy
    0.08
    Activations Density 0.005%

    No Known Activations