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. 30636
    Prev
    Next
    INDEX
    Explanations

    5-second rule

    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
     coloc
    -0.08
     Pupp
    -0.07
    �
    -0.07
     concent
    -0.07
    Haz
    -0.07
     Mejor
    -0.07
    Tender
    -0.07
     reh
    -0.07
    _TER
    -0.07
    PRECATED
    -0.07
    POSITIVE LOGITS
     influx
    0.09
    .inline
    0.07
    Creator
    0.07
     expl
    0.07
     exploding
    0.07
    690
    0.07
     Dt
    0.07
    664
    0.07
     обучение
    0.07
     события
    0.07
    Activations Density 0.001%

    No Known Activations