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. 111870
    Prev
    Next
    INDEX
    Explanations

    Trust

    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
     Wettbewer
    -0.10
     compete
    -0.09
    tablet
    -0.09
     tumor
    -0.09
     Paging
    -0.08
     konkurr
    -0.08
     Konkurrenz
    -0.08
     competitor
    -0.08
     competit
    -0.08
     concurso
    -0.08
    POSITIVE LOGITS
     trust
    0.17
     trustworthy
    0.16
     Trust
    0.15
    trust
    0.15
    Trust
    0.15
     distrust
    0.15
     trusting
    0.15
     Vertrauen
    0.14
     confiar
    0.14
     trusted
    0.14
    Activations Density 0.032%

    No Known Activations