Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 58612
    Prev
    Next
    INDEX
    Explanations

    resist

    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
     ר
    -0.08
     пузыр
    -0.08
     اعتماد
    -0.07
     distint
    -0.07
    Precision
    -0.07
     indis
    -0.07
     chu
    -0.07
     cic
    -0.07
     Precision
    -0.07
     Facilit
    -0.07
    POSITIVE LOGITS
     urge
    0.10
    力度
    0.10
     сопротив
    0.10
     resistência
    0.09
     urges
    0.09
     résistance
    0.09
    拒
    0.09
     unlawful
    0.09
     resisting
    0.09
     resistance
    0.08
    Activations Density 0.010%

    No Known Activations