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. 11-RESID-POST-AA
    6. 24271
    Prev
    Next
    INDEX
    Explanations

    Two

    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
    	F
    -0.08
    ðun
    -0.08
    USTER
    -0.08
     pension
    -0.08
     abolition
    -0.08
     آز
    -0.08
    .First
    -0.08
     pensions
    -0.08
     abandonment
    -0.08
     særlig
    -0.07
    POSITIVE LOGITS
     guide
    0.08
     quickly
    0.08
     guia
    0.08
    highlight
    0.08
     guiding
    0.08
    공지
    0.08
     rápidamente
    0.07
     mul
    0.07
     мост
    0.07
     guided
    0.07
    Activations Density 0.024%

    No Known Activations