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. 18972
    Prev
    Next
    INDEX
    Explanations

    square root function

    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
     gone
    -0.08
    .Ob
    -0.07
     montrer
    -0.07
    akit
    -0.07
    :y
    -0.07
     faciles
    -0.07
    :`
    -0.07
    ’aff
    -0.07
    732
    -0.07
     part
    -0.07
    POSITIVE LOGITS
     sea
    0.08
    cripcion
    0.08
    тым
    0.08
     qabu
    0.08
     diferente
    0.08
    தும்
    0.08
     vastaan
    0.08
     odnosno
    0.07
     {↵//↵//
    0.07
                                
    0.07
    Activations Density 0.009%

    No Known Activations