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. 23-RESID-POST-AA
    6. 131000
    Prev
    Next
    INDEX
    Explanations

    resilience, resistance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fresh
    -0.07
     Conven
    -0.07
    	unset
    -0.07
     কমিশ
    -0.07
    旬
    -0.07
     delo
    -0.07
    unset
    -0.07
    直选
    -0.07
     mila
    -0.07
     täh
    -0.07
    POSITIVE LOGITS
     resilience
    0.55
     resilient
    0.51
     resistentes
    0.47
     resistente
    0.46
     resil
    0.44
     resistencia
    0.42
     résistance
    0.41
     resistant
    0.41
     résist
    0.41
     resistência
    0.40
    Activations Density 0.192%

    No Known Activations