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. 49253
    Prev
    Next
    INDEX
    Explanations

    }

    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
    GB
    -0.09
     specifications
    -0.08
     chassis
    -0.08
    ã
    -0.08
    .jpg
    -0.07
    YYYY
    -0.07
    �
    -0.07
     ruled
    -0.07
     propulsion
    -0.07
     healed
    -0.07
    POSITIVE LOGITS
     notoriously
    0.10
     citar
    0.10
    累计
    0.10
     famously
    0.10
     cumulative
    0.09
    _iterator
    0.09
     infamous
    0.09
     notorious
    0.08
     approximation
    0.08
     bronnen
    0.08
    Activations Density 0.024%

    No Known Activations