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. 106352
    Prev
    Next
    INDEX
    Explanations

    resilience

    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
     सौ
    -0.08
     nada
    -0.08
    oben
    -0.07
    五星
    -0.07
     acidity
    -0.07
    .SIZE
    -0.07
     cab
    -0.07
    amen
    -0.07
    _INTERFACE
    -0.07
     Santos
    -0.07
    POSITIVE LOGITS
     resilience
    0.11
    Against
    0.09
    ilience
    0.08
     resilient
    0.08
     Against
    0.08
     bordering
    0.08
     resil
    0.08
     구축
    0.08
    ful
    0.08
     constit
    0.08
    Activations Density 0.007%

    No Known Activations