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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19727
    Prev
    Next
    INDEX
    Explanations

    say "classical"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     или
    -0.10
     различных
    -0.10
     or
    -0.09
     разных
    -0.09
     розных
    -0.09
     йәки
    -0.09
     генера
    -0.09
    หรือ
    -0.09
    _changed
    -0.09
    -0.09
    POSITIVE LOGITS
    	util
    0.08
     servizi
    0.08
    heritance
    0.07
     valt
    0.07
     Yer
    0.07
    Services
    0.07
     fisc
    0.07
     bunda
    0.07
    YX
    0.07
    	properties
    0.07
    Activations Density 0.001%

    No Known Activations