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. 117356
    Prev
    Next
    INDEX
    Explanations

    physics and code

    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
    ->{
    -0.08
     habilidade
    -0.07
     Hydro
    -0.07
    itsy
    -0.07
    .Fatalf
    -0.07
    .flatten
    -0.07
    .print
    -0.07
     shm
    -0.07
    	DECLARE
    -0.07
    ♫
    -0.07
    POSITIVE LOGITS
     परिणाम
    0.08
    parking
    0.08
     úč
    0.08
     signed
    0.08
     edit
    0.08
     पार्क
    0.08
     studie
    0.07
    hasil
    0.07
     मुकाब
    0.07
     parking
    0.07
    Activations Density 0.001%

    No Known Activations