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. 54173
    Prev
    Next
    INDEX
    Explanations

    Overshooting

    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
     garantia
    -0.08
     underserved
    -0.08
     catering
    -0.08
     scandals
    -0.07
     garantía
    -0.07
     caters
    -0.07
     chair
    -0.07
     antenna
    -0.07
     mornings
    -0.07
    fform
    -0.07
    POSITIVE LOGITS
    Reached
    0.10
    Exceeded
    0.09
     jumping
    0.09
    overs
    0.08
     jumped
    0.08
    _match
    0.08
     Jump
    0.08
    Overs
    0.08
     crossing
    0.08
     leap
    0.08
    Activations Density 0.024%

    No Known Activations